AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform
This addresses pest monitoring for agriculture, but it is incremental as it applies existing object detection methods to a specific domain.
The study tackled real-time object detection for fruit flies in remote insect traps using on-the-edge deep learning, finding that SSD-MobileNetV2 achieved an AP@0.5 of 1.0 and YOLOv4-tiny outperformed with 1.0 AP@0.5 but had slower throughput, with SSD models enabling real-time detection on Raspberry Pi.
Fruit flies are one of the most harmful insect species to fruit yields. In AlertTrap, implementation of Single-Shot Multibox Detector (SSD) architecture with different state-of-the-art backbone feature extractors such as MobileNetV1 and MobileNetV2 appears to be potential solutions for the real-time detection problem. SSD-MobileNetV1 and SSD-MobileNetV2 perform well and result in AP at 0.5 of 0.957 and 1.0, respectively. You Only Look Once (YOLO) v4-tiny outperforms the SSD family with 1.0 in AP at 0.5; however, its throughput velocity is considerably slower, which shows SSD models are better candidates for real-time implementation. We also tested the models with synthetic test sets simulating expected environmental disturbances. The YOLOv4-tiny had better tolerance to these disturbances than the SSD models. The Raspberry Pi system successfully gathered environmental data and pest counts, sending them via email over 4 G. However, running the full YOLO version in real time on Raspberry Pi is not feasible, indicating the need for a lighter object detection algorithm for future research. Among model candidates, YOLOv4-tiny generally performs best, with SSD-MobileNetV2 also comparable and sometimes better, especially in scenarios with synthetic disturbances. SSD models excel in processing time, enabling real-time, high-accuracy detection.