Wildlife Data Collection and Analysis

A walkthrough of the wildlife data collection process and insights.

1. Data Collection

• We deployed 4 camera traps for 7 months; from June 2021 to December 2021
• 8524 images were annotated and published
• 8254 images from the Raspberry Pi 2 and 610 from the Pi Zero
• 325 images from the Open MV Cam H7
• All the images are in JPG format

2. DSAIL-Porini Dataset

Species captured:

1. Defassa waterbuck
2. Sykes' monkey
3. Common warthog
4. Bushbuck
5. Burchell's zebra
6. Impala

3. Data Annotation and Challenges

The data annotation for the DSAIL-Porini dataset was manual with the following challenges:

• Animals overlapping in an image
• Sometimes an animal would have been captured while its body was in the frame partly
• Some images were too far and not visible, especially if the grass had grown too long
• Some images were too dark
• Lens flare: this degraded the quality of some images
• Time-consuming process
• Determining the sex of animal species like the zebra, warthog and monkey was difficult

4. DSAIL-Porini Sample Images

These are other samples of images collected from the conservancy:

5. Data Analysis

From the data that was collected, we performed some analysis to get a better understanding of the data.

6. Value of Data

The data collected can be used to:

• Train machine learning models for classification and object detection
• Train and test image-based census algorithms as it includes animal counts
• Understand animal behaviour
• Estimate the animal population growth with time

7. Understanding Animal Behaviour

• We painted the camera traps green to camouflage them
• We got more close-ups of animals like the waterbuck

8. Camera Trap Placement

The decision to place the camera traps in these locations was based on:

1. Locations where mineral supplements were provided for the animals
2. Trails that led to water holes in the conservancy and areas near the waterholes
3. Any other place where water would be provided by the wardens