Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities
Our aim is to promote the widespread use of electronic insect traps that report captured pests to a human-controlled agency. This work reports on edge-computing as applied to camera-based insect traps. We present a low-cost device with high power autonomy and an adequate picture quality that reports...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/5/2006 |
| _version_ | 1797473715765641216 |
|---|---|
| author | Ioannis Saradopoulos Ilyas Potamitis Stavros Ntalampiras Antonios I. Konstantaras Emmanuel N. Antonidakis |
| author_facet | Ioannis Saradopoulos Ilyas Potamitis Stavros Ntalampiras Antonios I. Konstantaras Emmanuel N. Antonidakis |
| author_sort | Ioannis Saradopoulos |
| collection | DOAJ |
| description | Our aim is to promote the widespread use of electronic insect traps that report captured pests to a human-controlled agency. This work reports on edge-computing as applied to camera-based insect traps. We present a low-cost device with high power autonomy and an adequate picture quality that reports an internal image of the trap to a server and counts the insects it contains based on quantized and embedded deep-learning models. The paper compares different aspects of performance of three different edge devices, namely ESP32, Raspberry Pi Model 4 (RPi), and Google Coral, running a deep learning framework (TensorFlow Lite). All edge devices were able to process images and report accuracy in counting exceeding 95%, but at different rates and power consumption. Our findings suggest that ESP32 appears to be the best choice in the context of this application according to our policy for low-cost devices. |
| first_indexed | 2024-03-09T20:20:24Z |
| format | Article |
| id | doaj.art-65c2a5b4ff3a4f5abca1d99f6fecc517 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T20:20:24Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-65c2a5b4ff3a4f5abca1d99f6fecc5172023-11-23T23:49:41ZengMDPI AGSensors1424-82202022-03-01225200610.3390/s22052006Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart CitiesIoannis Saradopoulos0Ilyas Potamitis1Stavros Ntalampiras2Antonios I. Konstantaras3Emmanuel N. Antonidakis4Department of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceDepartment of Music Technology and Acoustics, Hellenic Mediterranean University, 74100 Rethymno, GreeceDepartment of Computer Science, University of Milan, 20133 Milan, ItalyDepartment of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceOur aim is to promote the widespread use of electronic insect traps that report captured pests to a human-controlled agency. This work reports on edge-computing as applied to camera-based insect traps. We present a low-cost device with high power autonomy and an adequate picture quality that reports an internal image of the trap to a server and counts the insects it contains based on quantized and embedded deep-learning models. The paper compares different aspects of performance of three different edge devices, namely ESP32, Raspberry Pi Model 4 (RPi), and Google Coral, running a deep learning framework (TensorFlow Lite). All edge devices were able to process images and report accuracy in counting exceeding 95%, but at different rates and power consumption. Our findings suggest that ESP32 appears to be the best choice in the context of this application according to our policy for low-cost devices.https://www.mdpi.com/1424-8220/22/5/2006e-trapspest detectionimage sensorsedge computing |
| spellingShingle | Ioannis Saradopoulos Ilyas Potamitis Stavros Ntalampiras Antonios I. Konstantaras Emmanuel N. Antonidakis Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities Sensors e-traps pest detection image sensors edge computing |
| title | Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities |
| title_full | Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities |
| title_fullStr | Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities |
| title_full_unstemmed | Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities |
| title_short | Edge Computing for Vision-Based, Urban-Insects Traps in the Context of Smart Cities |
| title_sort | edge computing for vision based urban insects traps in the context of smart cities |
| topic | e-traps pest detection image sensors edge computing |
| url | https://www.mdpi.com/1424-8220/22/5/2006 |
| work_keys_str_mv | AT ioannissaradopoulos edgecomputingforvisionbasedurbaninsectstrapsinthecontextofsmartcities AT ilyaspotamitis edgecomputingforvisionbasedurbaninsectstrapsinthecontextofsmartcities AT stavrosntalampiras edgecomputingforvisionbasedurbaninsectstrapsinthecontextofsmartcities AT antoniosikonstantaras edgecomputingforvisionbasedurbaninsectstrapsinthecontextofsmartcities AT emmanuelnantonidakis edgecomputingforvisionbasedurbaninsectstrapsinthecontextofsmartcities |