Detecting poachers through Sound Event Recognition

Anti-poaching

In 90 seconds this video shows you how the SERVAL can be used to detect threats, such as poachers or illegal loggers.

Human-Wildlife Conflict

Another promising application of SERVAL is the mitigation of the human-wildlife conflict. Habitats of elephants shrink, seducing them to roam into the land and villages of farmers living near nature reserves. This is causing serious trouble. Villagers loose their crop, or worse, get killed. In retaliation, elephants get poisoned or shot. By identifying and localising elephants before they enter the human territories, rangers may be in time to keep both the villagers and the elephants safe.

For this project, we are working closely together with:

• Karol Piczak of the Warsaw University of Technology,

• Angela Stoeger-Horwath of the Dept. Cognitive Biology, Vienna University,

• Matthias Zeppelzauer of the St. Pölten University of Applied Science,

• Peter Wrege of the Elephant Listening Project at Cornell University, and

• Blaise Droz, independent nature journalist and videast.

Smart Vision update

Noah and friends have done it! The Open CV (computer vision) is running on a Raspberry Pi. To ensure that the system performs well in real-time they had to “overclock” the system and to add a heat-sink to prevent the chip from burning. The result is a fast, low-cost and low-energy smart camera that can be used for wildlife census and anti-poaching missions.

The recognised ‘objects’, in our case, are humans, elephants, tigers, and other species. The outcome is communicated with Cluey to inform park rangers in real-time. The data may also be used by census-researchers. In that case the classified images may be collected periodically.

Below you see the sneak-preview of the cloud-based smart-cam training console. This console may be used by experts or the public to improve our classifier (for the experts: we use a mix of classic learning, machine learning, and deep learning). Once the detection accuracy of the smart-cam is sufficient, the sensor can be placed in the field. To reduce communication cost, only the class will be send. To increase confidence in the system, a thumbnail of the recognised object may be send as well.

Can’t wait to experiment with the smart cam? Feel free to contact us to discuss how we can speed up time to the field!

DIY Smart Computer Vision

The problem

If you have a camera to detect burglars, an alarm system to detect opening doors, and a smoke detector to alert you in case of fire, wouldn’t it be nice if all these systems could be presented to you through one simple app? If you already have an integrated system like that, you probably bought all of the components at the same supplier. Adding third-party or Do-It-Yourself (DIY) sensors, or combining the data with other data sources, such as weather stations or the GPS-position of your mobile phone, is probably hard or impossible. Options to combine the data, however, would enable you to make your systems really smart…

The solution

To allow you to connect any type of sensor you wish, we are developing an open source Application Programming Interface (API). Any hobbyist or programmer can use it to connect his of her own device to the SCCSS-sensing platform. From there, the data may be presented in Cluey or WildCAT, or exported to CSV, XML or JSON, for further analysis.

Low-cost Smart Computer Vision Camera

A first trial project has been adopted by 4 students of Technasium Keizer Karel College Amsterdam. Noah, Robin, Celio and Dimme have the ambition to turn a standard webcam into a low-cost Smart Computer Vision Camera. That’s a camera which does not just take pictures, but which can be trained to takes pictures only when a person walks along, or a dog, tiger, elephant, or whatever else it has been trained for. Once the object of interest has been detected, a small image is created and sent to the Cluey-app.

A tough task, involving the mastering of Open Source Computer Vision software on a Raspberry Pi, Python programming, a little engineering, and lots of endurance, fun and enthusiasm!

Noah, Robin, Celio and Dimme expect to finish the project this summer. They will publish the source code and the “How to” in GitHub, thus making it available to the public for free.

The first results are looking good!

Screen print: Noah captured by the team’s engineering masterpiece, the low cost Smart Computer Vision Camera!

Sensing Clues at TEDx!

You should listen to the TEDx-talk I held at TEDxRotterdam last November,

• if you feel angered about elephants being killed for their ivory,

• if you want to be challenged to do something about it – by doing what you know best!

Looking forward hearing from you!

Jan-Kees Schakel, CEO Sensing Clues

ps please share the story with your friends!

Sensing Clues goes to Nepal!

After a summer of hardcore development, Sensing Clues is ready for the next step. Together with the Himalayan Tiger Foundation we’ll travel to Nepal to examine and demonstrate the potential of our sensor and real-time intelligence tools. Think of:

• passage detection,

• lingering detection,

• group size detection,

• first-time seen detection,

• light-beam detection,

and many other profiles which can be used to inform rangers of alarming occurrences in protected areas. Following is a short summary of what we did this summer.

The Trespasser, a sensor designed to detect electronic devices, has reached it next level of maturity. In a pilot study conducted with the Dutch National Forestry Department we were able to detect the difference between hikers passing a nest of a protected hawk and people lingering near the nest. Based on the number of devices we could estimate the number of persons at the scene. This is an important feat, as “big-5 poachers” often work in groups of 3 to 4 persons. Recognizing the number of people lingering near a waterhole or other critical spots thus gives rangers an early warning of a threatening situation.

Our new Serval-soundscape sensor has passed its first milestones. Data acquisition, a tech-word for recording and storing the sounds in a ready-to-process format, is ready. So is the store-in-memory function that ensures that sounds do not get wasted when connectivity is lost for a while. The next step is to incorporate the recognition algorithms and to establish connectivity. Both are within reach. As soon as time and funds permit we will start field-testing.

Power supply is a critical issue when working in remote areas. As there is no off-the-shelf solar solution that meets our tough outdoor requirements, which includes proper camouflaging to avoid detection by poachers, we needed to develop a tailor-made solution. The good news is: we did. The first results are promising. In two days time the solar panel is able to load a car battery that keeps the sensor alive and kicking for over 6 weeks. Hence, protection operations of 3 to 6 months have become within reach.

In the mean time we experimented with the setup of a LoRa-network. Such networks are comparatively cheap and can be deployed where cellphone coverage is lacking. As with all technology, the road to full-scale use is bumpy. If not properly configured, reaching a proper range is troublesome. Knowing the problem is half the solution. So we are now working on the second half.

All that being said, most of our time was spent on the development of Cluey, our fast-response coordination app, and its backend, which in fact constitutes an affordable sensing-and real-time analytics platform and intelligence tools. Our platform constitutes a dozen servers, software packages, has very high security standards, and is maintained by our engineers. Regularly, such systems are prohibitively expensive for a single park or NGO. By offering the platform as a service, however, we bring it within reach of even the most modest NGO.

Ps. local governmental organisations in the Netherlands have shown an interest in these tools also, which accelerates their development!

Our hawks have left their nest – mission completed!

Mission completed! This weekend the young hawks stretched their wings and made their first flight.

For almost two months the rangers in the Southern Netherlands have been on the alert for poachers, as the nest has been robbed for several successive years. Local bird lovers complained, but the problem was difficult to tackle. Attempts to catch the poachers through camera traps failed, as the cameras were stolen.

This year a Trespasser was hidden near the birds-nest to notify the rangers when people would come near. The sensor triggered 16 times. Based on a smart algorithm we are able to determine whether a detected person is bypassing or lingering at the scene. We were especially interested in the latter, which happened twice. The first time was on the first of June, when the young were still very small. Great was our relieve when it proved to be one of our rangers checking whether the birds were still safe. The second time foresters were busy marking trees near the nest.

Now the birds have left their nest on their own – the first time since years. We are so happy about it! A pity that we didn’t catch a poacher, but so be it. The sensor operated well and unattendedly for over 6 weeks. The rangers are enthusiastic about them as the sensors can distinguish between people and other moving targets and can be placed completely out of sight (see photo below – just try to find it 

Time to celebrate and move on to the next project!

The clock is ticking…

About one week to go before the young of our hawks will fly out and discover the world! So far we managed to shield off the poachers, who have been stealing chicks for years.

It’s a project in which we learn while doing. As we knew, in fast-response organizing every second is of the essence. Easy to say. Quite complex to accomplish technically.

Today we scrutinized the process steps from signal detection to alert. A process which from sensor to end-user app covers over 15 time critical components.

First LoRa field-tests for the protection of endangered birds

Placing the LoRa gateway antenne

Today we have set up our first LoRa-network for the Dutch National Forestry Departement. In the next two months we are testing the communication between the gateway, the outdoor field sensors, and our secure cloud services.

Concurrently we installed two Trespassers for the protection of endangered birds of prey. The last few years they have been robbed of their young by poachers. Together with the rangers of the State Forestry Department we aim at keeping them safe.

Testing connectivity with our secure cloud services

Testing connectivity in the forest

Wildlife Conference The Hague

From 1 to 3 March the Dutch Ministry of Economic Affairs hosted an international conference on wildlife. A broad range of stakeholders were invited to accelerate action against wildlife crime. Sensing Clues was there!

The theme of the conference was: Action, or game over! We choose ACTION! Several “Wildlife deals” were made.

First of all we are honoured to have been invited by the Minister of Sustainable Development and Wildlife of Sri Lanka to explore the strengths of our sensor systems to protect their wildlife from poachers. A visit will be organised to demonstrate our tools in the field and to discuss tactical deployment.

We are also very much honoured to have been invited by the Ambassador of Bangladesh to help them  protecting tigers in the Sundarbans mangrove forests. Field visits will be organised to ensure that our plans build on their existing expertise and suite their unique local requirements.

We concluded a Wildlife Deal with Smart Parks, a research project led by the Resource Ecology Group of Wagening University and a reserve in South Africa. The project aims at  detecting poachers through the interpretation of (real-time) geospatial behaviour of herbivores (prey). Through our extensive knowledge of secure networks, cloud computing, and mesh-networks in low- or no-tech environments, Sensing Clues aims at preparing a future-proof base for these powerful tools.

Another Wildlife Deal was made with NSCR and the African Parks Network. As Andrew Lemieux of NSCR said: “Reporting is dead, we need prevention briefings based on data analysis.”. We explore opportunities to create a Wildlife Crime Analyst Toolbox (Wild CAT). Sensing Clues supports this project through the design of dummy-proof graphical user interfaces, and the provision of private and secure big-data analytics hosting services.

Other deals are in the making with amongst others NFI and the Netherlands Consulate in Nepal. We look back at a fruitful conference. It’s good to see and feel how individual strengths are being united against wildlife crime! Follow us on twitter and Facebook to be kept up to date about our progress and the successes we achieve in turning wild spaces into safe havens!

Safe and sound

Sound Event Recognition-based Vigilance for Alerting and Localisation.

Where humans are, there is noise. Although rowdiness of humans may be irritating, we use it in our favour. Indeed, poachers too make noises that give them away. The challenge is whether we are able to distinguish between ‘normal’ human sounds and those of poachers at work. And, of course, whether we can pick up these sounds in remote and desolate areas.

To determine the meaning of a sound, one has to interpret it. The sound of a car, for example, may be very common in areas where people go on safari, but much less so at night. This is true for most types of sounds. Their meaning varies with its context.

To develop a smart sensor which can interpret contextualised sounds, SensingClues sought the help of M+P (see earlier post) and Sensory Cognition Group of the Rijksuniversiteit Groningen. Both are reputable for their acoustic expertise. Both accepted the challenge.

The working name for our sound sensor is SERVAL, an acronym for Sound Event Recognition-based Vigilance for Alerting and Localisation. Once we finished the design we will search for a funds to develop it, and add it to our anti-poaching toolkit. 

We help rangers to turn wild spaces into safe havens!

Kasigau: poachers detected!

Tsavo East, Tsavo West, and the Kasigau Wildlife Corridor which connects them form the largest natural reserve in Kenya. Elephants, lions, giraffe, and many other species roam the area freely. It’s a lust for the eye. A treasure to cherish!

A real threat to this paradise is poaching. Not only to the animals, but also to the (unarmed) rangers that protect them. Two years ago two of them were shot by poachers. One ranger was killed. The other survived, but has a prosthetic shoulder since. This hero is still a ranger.

To help the rangers to stop poaching, SensingClues joined Tech-For-Tusks, a  project in which Wildlife Works, ShadowView, ProTrek, Microflown, NCSR, and SensingClues collaborate to protect elephants. After months of hard work, this was a very exciting opportunity to test our newly developed early warning system.

With baboons looking over our shoulders, long days and nights were spend to test, improve, and re-test our sensors. Until we were satisfied. Since this weekend our camouflaged sensors are on the alert for poaching activities. Tireless. Relentless. Once a poacher is detected, an alert is send to the patrolling rangers, directing them straight away to the actual threat.

Last Wednesday, only days after the sensors had been placed, the first alert came through. Human behaviour had been detected near a pond which elephants regularly visit. Being a restricted area, no people are allowed there. Verification learned that it was not a ranger. Hence, this was an all hands on deck situation!

A short while later we learned our poacher was actually a lost soul, taking her father on a safari. Although we were a bit disappointed with this outcome, the system had proven its strength. We’ve been able to detect human activity and alert the rangers in real-time!

It’s a really nice feeling to put the rangers on the right track. It’s good to know they are on the alert and ready to respond..

SensingClues is going to protect Nguvu!

Last week was a fantastic week!

• for Nguvu, because our early warning and fast-response systems are going to help rangers to keep him and his family safe;

• for SensingClues, because we gained our first contract!

SensingClues is partnering with Wildlife Works, ShadowView, Protrek and NSCR in the Tech for Tusks project. The project aims at developing and testing hi-tech systems to protect elephants in the Kasigau Wildlife Corridor, Kenya. We bring in our expertise and early warning and fast-response technologies.

The last few months we have been working hard to make our technologies ready. We’ve tested and demonstrated them in the Netherlands. Our potential customers and techno team were satisfied. So, now it’s time to test them in the harsh conditions of the African bush! Recent incidents, including ones that made the world-wide press, urge us to wast no more time.

The project is starting mid October. The tests will take about one month. We’ll keep you posted through  Twitter and this blog!

Detecting presence of bush crafter

In a southern nature reserve in the Netherlands, the State Forestry Department has spotted a tree hut, made by a bush crafter. In its neighbourhood rangers have found snares, suggesting that the bush crafter is also a poacher.

Because the rangers are too few in number, the forests too extensive, and the visits of the bush crafter irregular, hiding and waiting until the bush crafter arrives is not an option.

Hence, the local ranger suggested us to test our Trespasser sensor here. The idea was simple: we would hide our sensor near the tree hut. Once someone would stay near that hut for more than 15 minutes, an alert would be send to the rangers, enabling them to catch him red-handedly.

So we did. This week we placed the sensor. However, it did not come online. A small investigation learned us that network roaming was the problem. Indeed, the area was very near the German border. It is a minor problem, but to fix it we had to take the sensor back.

Conclusion: this time the bush crafter was lucky. But not for long. We’ll be back shortly. From then on our sensor will inform the rangers when the bush crafter arrives at the scene…

Sensor-journey day

The challenge:

Measure the presence of a poacher at work and send an alarm to a group of fast-responders.

The solution:

You want to use the technology without worrying about its complexities. Like your computer or phone: it should just work! We took that at heart and have been working on it for several months now. With a little help of our partners we developed a first beta-version of a human-presence detection sensor, a web-based intelligence platform (SCCSS), and Cluey, our fast-response app. Today the sensor measurements completed the full journey – a memorable moment!

Within a few weeks we will be testing our solution in the Dutch forests. Within a few months this technology will have matured enough to be tested in the tough operational field conditions of Kenya.

M+P announces its partnership with SensingClues

M+P announces its partnership with SensingClues:

The wilderness should become a safe place for wildlife again. At the moment it is not because of poachers and other hostile human activities. SensingClues develops solutions for this problem. Recently, we have become a strategic partner for them. Together we develop smart sound- and vibration sensors that can track human threats at an early stage so that authorities can take appropriate action.

Read the full English version.

Lees de volledige Nederlandstalige versie.

We are partnering with MarkLogic!

As of today we are working with MarkLogic to develop our SensingClues Cloud Services Suite (SCCSS). Our first tool in this suite is FOCUS. FOCUS is an interactive real-time big-data analytics tool. It is designed to support heuristic analysis, performed by crisis response decision makers, rather than data scientists. As such it is the tool for both centralised and distributed field operations’ intelligence and command centers.

MarkLogic is the only Enterprise NO-SQL database (Not Only SQL). It is a rocketing new generation storage and retrieval tool that is built for dealing with today’s high variety of data, high volumes, and high velocities. In other words, designed for big data. Think sensor data, geographical data, open source social media data, geo-tagged photo’s, etc. Anything that can be used to inform decision making within fast response teams. And very important for supporting collaboration between stakeholders in the field: data security is built in. We thus can guarantee that information is only shared with those entitled. And we can share information across organisational boundaries without losing that control.

In short, as of today SCCSS is powered by MarkLogic !

Bridge the gap!

Poachers, illegal loggers, and the like weigh their potential gain against the risk and price of being caught. By catching them red-handedly, all evidence is present for conviction. Raising the chance of being caught, discourages poachers. But how can we increase the chance of apprehension?

Approaching the problem from an information, knowledge and expertise coordination angle, we identified 6 gaps that have to be bridged in order to be successful. Through advice and hands-on help,  SensingClues helps you to bridge these gaps.

1: the alerting gap

When did you learn about the threat? And when did it actually start? Knowing what is happening and when it is happening is crucial for catching poachers in the act. Our human senses are very localised and restricted to seeing, hearing, feeling,  tasting, and smelling. Technological sensors can do all that. In addition, they perform 24/7 and extend senses to ranges that cannot be heard, seen or perceived by our human senses.

Sensor-technology challenges are manifold, but solvable. First, you have to know what discriminates poaching behaviour from other forms of human behaviour. Second, you have to think about clever ways to detect them: what sensor can be used, where should they be positioned. And third, you have to make the sensor-data available in real-time. In remote areas this can be quite difficult. The sensors have to be connected to the web, self-supporting in energy, and robuust enough to withstand its environment. More and more promising examples become available (e.g. chainsaw and tresh-passing detection).

SensingClues believes that no-one can stop the ongoing slaughter of precious species alone. If we want to be effective, we must collaborate. It’s time to join forces! Hence, we work with a wide range of partners to make technologies available and affordable to protectors all over the world. To stimulate collaboration we are developing the SensingClues Cloud Services Suite – SCCSS (pronounced as ‘success’), thus avoiding that users have to acquire, install, learn, and maintain a multitude of systems.

2: the intelligence gap

Intelligence is actionable information that gives you the edge over your opponent. Intelligence enables you to out-smart poachers. The question is: how good are you at collecting data? in using it to create intelligence? and in leveraging it to the rangers and other protectors in the field? With divers data sources, formats, forms of ownerships, etc., this question is not easily solved.

To integrate, handle, analyse, and leverage the information we are developing an interactive real-time intelligence tool, FOCUS. By structuring 5 key-elements of data that inform action, the tool helps to focus on what is important to start and coordinate a fast response.

FOCUS is especially designed for fast-response professionals and does not require statistical or technological skills, as is often the case in business intelligence software. It also allows for distributed access and collaboration, as may be expected from a net-centric solution.

3: the action repertoire gap

Responding to a threat may be very complicated when the poachers are larger in numbers, armed, and dangerous. Or if they are simply out of reach due to the distance that has to be bridged. Working together with non-professional first-responders is delicate, but possible. This may start by asking people in the area to function as “eyes and ears” of law enforcers. But other tasks such as scaring away animals or creating blockages are within reach.

SensingClues has developed the SCUM-method to explore effective strategies involving multiple partners.

4: the response-time gap

Poachers preferably work when protectors are far away or off-duty. The time needed to formulate an appropriate response and mount an operation, is used by poachers to escape. Thus, a short response-time is critical.

Based on the principles of net-centric organising, SensingClues provides hand-on advise to decrease the response-time gap.

5: the evidence gap

Often poachers are gone by the time rangers arrive at the scene. But they seldom left without a trace. Knowing how to approach a poaching site safely, and to gather and preserve forensic evidence that may later be used in court, is critical.

Through our network of law enforcement professionals we can organise “art of inspection” workshops and provide field training to rangers.

 6: the technology gap

Technology is a sine-que-none factor in developing effective poaching solutions. Without proper technology, such as sensors, drones, information and communication technology, and coordination technologies, protectors make no chance to beat poachers. The challenge is the last mile. That is, from the internet and office environment to the user in the field: point-to-point real-time interaction, while all points are moving from one place to another.

It’s our strength and pride to help our partners to bridge that last mile.

Kickoff meeting Sensing Clues

Last Friday we organized our first SensingClues kickoff session! Nine highly qualified and enterprising specialists were invited to hear about our ambitions. And to explore opportunities to join or collaborate. Indeed, our mission to turn wild spaces into safe havens requires a cutting edge and daring team plus a network of skillful partners!

Of course we ran out of time. But it was enough to convince everyone present that SensingClues’ mission and business model are inspiring, solid, and manageable. On the 5th of June we will continu our talks.

SensingClues has been selected for the BizSparks startup program of Microsoft!

We received good news from Microsoft. Our startup has been elected for the BizSparks program for startups! The result is that we can make free use of many Microsoft tools to develop our SensingClues Cloud Services and App’s. For three years! This is what we call a kick start 

Hello world, SensingClues is live!

Friends!

SensingClues has been launched. As of today we start developing our services to turn wild areas into safe havens for wildlife. What a happy day this is!

Through this medium we will keep you posted of our projects. Take your time to check-out our website and let us know what you think.

We believe that if all involved in protecting wildlife alliance against poaching, we should be able to accomplish our mission. We have no time to loose, let’s get going!