Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2021
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2112.13341 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913787710275584 |
|---|---|
| author | Le, An D. Pham, Duy A. Pham, Dong T. Vo, Hien B. |
| author_facet | Le, An D. Pham, Duy A. Pham, Dong T. Vo, Hien B. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2112_13341 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform Le, An D. Pham, Duy A. Pham, Dong T. Vo, Hien B. Computer Vision and Pattern Recognition 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. |
| title | AlertTrap: A study on object detection in remote insects trap monitoring system using on-the-edge deep learning platform |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2112.13341 |