Abstract A target‐specific bait dispenser is required for oral bait vaccination of the endangered Tasmanian devil ( Sarcophilus harrisii ) against the deadly devil facial tumour disease. Development of a broadly extendable dispenser would be a beneficial ecological tool. An edge device is a low‐power computing system designed to collect and process data at the source. A camera‐based edge device with a deep learning model can be used to identify the target species using image classification. It is important to choose a suitable edge device for the dispenser's effective application under remote field conditions. We evaluated four edge devices for the smart bait dispenser: ArduinoPro Nicla Vision, ArduinoPro Portenta H7 with Vision Shield (LoRa), Raspberry Pi 3 Model B+ and Raspberry Pi Zero 2 W. Two simple convolutional neural networks and four fine‐tuned pretrained models (MobileNetV2, MobileNetV3Small, ResNet50V2 and ResNet152V2) were trained on trail camera images of devil and non‐devil species. These models were evaluated across four metrics and post‐training quantised for deployment. The edge devices were assessed on inference latency of each model in seconds (s) and power consumption in watts (W). We found that a simple CNN‐based image classification model yielded the best overall result of ≈96% across all metrics. Using this model, all four edge devices were found to be quick enough for dispenser application (average inference latency of 0.42 s). Portenta consumed the lowest power during inference (0.19 W), idle (0.185 W) and light sleep (0.045 W) states, whereas Nicla Vision consumed the lowest power during deep sleep (0.002 W). Solution . We found that a simple traditional CNN was best suited for species classification in a camera‐based smart bait dispenser for vaccination of Tasmanian devils. For this application, ArduinoPro Portenta H7 with Vision Shield is the most competent device. We suggest integration of this system with a low‐power microcontroller unit to minimise inactive power consumption of the dispenser. This method can be readily adapted for other species in projects like vaccination and supplemental feeding.
Chaturvedi et al. (Thu,) studied this question.