A joint collaboration between The Prusten Project and Sensing Clues is underway to help reduce human-tiger conflicts. Using recently developed sensor technology called SERVAL, the two organizations are working to develop a sound-based tiger monitoring and early warning system to reduce conflict in tiger range-land countries. The sensors are also capable of recognizing gunshots and chainsaws in real-time providing a key tool in the fight against illegal wildlife activities.
More species are being threatened with extinction than ever before. To protect them we need to bring together and boost our strengths!
In regular life we use technologies to tackle all kinds of problems. So should we when it comes to the protection of wildlife.
The DataLab is a meeting space and hands-on laboratory for everyone interested in Data Science, Internet of Things (IoT) and Artificial Intelligence. A space to experiment, to develop and challenge new ideas.
Working together with professionals, scientists, and students, Sensing Clues uses the DataLab as incubator for data driven solutions for the protection of wildlife.
Curious? Below are two of the projects we are working on:
- Sound Event Recognition for Vigilance and Localisation (SERVAL)
- Wildlife Crime Analyst Toolbox (WildCAT)
Want to join one of our projects or to start a data-driven wildlife protection project of your own? Just drop us a note to start your expedition!
On Friday 7th July 2017 JADS will host the first-ever Wildlife Hackathon. During a full day of data- and brain-crunching activity, no less than 50 students and two data science teams of KPN and DIKW will dedicate themselves to find ways in which data can save some of the most threatened species in Africa.
The competing teams will be presented with two challenges. One presented by the Resource Ecology Group of Wageningen University. The other by Sensing Clues.
The challenge presented by Wageningen University is aimed at the preservation of rhino’s, by finding correlations between the time-spatial distribution and movement of zebra herds versus the presence of poachers wandering through the park. The brilliance of this approach is that the rhino’s do not have to be equipped with radio-beacons, which are easy to detect by professional poachers.
The challenge presented by Sensing Clues is aimed at reducing the conflict between humans and elephants. By accurately recognising the sounds of approaching elephants, villagers can be warned in time, thus preventing deadly confrontations (see also: SERVAL sensor). In this hackathon the students will be challenged to outperform the classifier created by Hugo, our most experienced data scientist.
This unique event is the result of a close collaboration between JADS and a Game Reserve in South Africa. Journalists interested in joining the event may contact Patricia Beks (p.beks at tue.nl / tel. + 31 (0) 6 31 242 757).
In 90 seconds this video shows you how the SERVAL can be used to detect threats, such as poachers or illegal loggers.
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,
- Shermin da Silva of Trunks & Leaves,
- 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.
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!
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…
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!
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!