Background
Camera traps have been used for a long time to capture images of animals in their natural habitat in a less, non-intrusive manner. These data collected can be used to carry out ecological research to increase understanding of species and habitat restoration practices.
At DSAIL, we have designed, developed and deployed 4 camera traps in the Dedan Kimathi Wildlife Conservancy to capture images of the mammalian species found there. The camera traps are based on low-cost hardware; the Raspberry Pi 2, the Raspberry Pi Zero and the OpenMV Cam H7 modules.
Accomplishments
We have an annotated dataset from these camera traps called DSAIL-Porini consisting of images of wildlife species from the conservancy. These species include the Burchell’s Zebra, impala, bushbuck, the Common warthog, Sykes’s monkey and the Defassa waterbuck. The dataset consists of 8524 images with 7589 images from the Raspberry Pi 2, 610 images from the Raspberry Pi Zero and 325 images from the OpenMV Cam H7. This dataset can be used to train machine learning models to detect, classify and segment images of animals. It can also be used to test censusing algorithms, understand animal behaviour, estimate animal population sizes, understand how animals interact, where they are likely to be found and how they feed.
We have deployed the camera traps in 18 locations in the conservancy so far.
Next Steps
We are working on getting more data from the conservancy while deploying in new locations. Furthermore, we are also planning on using machine learning to detect/classify the animals
Links
Dataset and annotations - https://data.mendeley.com/datasets/6mhrhn7rxc/6
Raspberry Pi software - https://github.com/DeKUT-DSAIL/cameratrap-pi.git
OpenMV Cam software - https://github.com/DeKUT-DSAIL/cameratrap-openmv.git
Publications
- Lorna Mugambi, Gabriel Kiarie, Jason Kabi , Ciira wa Maina Environmental Conservation
- DSAIL-Porini: Annotated camera trap image data of wildlife species from a conservancy in Kenya
- Data in Brief, January 2023
- Bibtex | Abstract | PDF | All