EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River
At present, the surveillance of river floating in China is labor-intensive, time-consuming, and may miss something, so a fast and accurate automatic detection method is necessary. The two-stage convolutional neural network models appear to have high detection accuracy, but it is hard to reach real-t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/4/2303 |
| _version_ | 1797622566887620608 |
|---|---|
| author | Lili Zhang Zhiqiang Xie Mengqi Xu Yi Zhang Gaoxu Wang |
| author_facet | Lili Zhang Zhiqiang Xie Mengqi Xu Yi Zhang Gaoxu Wang |
| author_sort | Lili Zhang |
| collection | DOAJ |
| description | At present, the surveillance of river floating in China is labor-intensive, time-consuming, and may miss something, so a fast and accurate automatic detection method is necessary. The two-stage convolutional neural network models appear to have high detection accuracy, but it is hard to reach real-time detection, while on the other hand, the one-stage models are less time-consuming but have lower accuracy. In response to the above problems, we propose a one-stage object detection model EYOLOv3 to achieve real-time and high accuracy detection of floating objects in video streams. Firstly, we design a multi-scale feature extraction and fusion module to improve the feature extraction capability of the network. Secondly, a better clustering algorithm is used to analyze the size characteristics of floating objects to design the anchor box, enabling the network to detect objects more effectively. Then a focus loss function is proposed to make the network effectively overcome the sample imbalance problem, and finally, an improved NMS algorithm is proposed to solve the object suppressed problem. Experiments show that the proposed model is efficient in detection of river floating objects, and has better performance than the classical object detection method and the latest method, realizing real-time floating detection in video streams. |
| first_indexed | 2024-03-11T09:13:09Z |
| format | Article |
| id | doaj.art-841f14ee0b8f4262b7a49d159f7ce568 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:13:09Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-841f14ee0b8f4262b7a49d159f7ce5682023-11-16T18:53:46ZengMDPI AGApplied Sciences2076-34172023-02-01134230310.3390/app13042303EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on RiverLili Zhang0Zhiqiang Xie1Mengqi Xu2Yi Zhang3Gaoxu Wang4School of Computer and Information, Hohai University, Nanjing 211100, ChinaSchool of Computer and Information, Hohai University, Nanjing 211100, ChinaSchool of Computer and Information, Hohai University, Nanjing 211100, ChinaSchool of Computer and Information, Hohai University, Nanjing 211100, ChinaState Key Laboratory of Hydrology–Water Resources and Hydraulic Engineering, Nanjing Hydraulic Research Institute, Nanjing 210029, ChinaAt present, the surveillance of river floating in China is labor-intensive, time-consuming, and may miss something, so a fast and accurate automatic detection method is necessary. The two-stage convolutional neural network models appear to have high detection accuracy, but it is hard to reach real-time detection, while on the other hand, the one-stage models are less time-consuming but have lower accuracy. In response to the above problems, we propose a one-stage object detection model EYOLOv3 to achieve real-time and high accuracy detection of floating objects in video streams. Firstly, we design a multi-scale feature extraction and fusion module to improve the feature extraction capability of the network. Secondly, a better clustering algorithm is used to analyze the size characteristics of floating objects to design the anchor box, enabling the network to detect objects more effectively. Then a focus loss function is proposed to make the network effectively overcome the sample imbalance problem, and finally, an improved NMS algorithm is proposed to solve the object suppressed problem. Experiments show that the proposed model is efficient in detection of river floating objects, and has better performance than the classical object detection method and the latest method, realizing real-time floating detection in video streams.https://www.mdpi.com/2076-3417/13/4/2303real-time object detectionvideo streamingmulti-scale feature |
| spellingShingle | Lili Zhang Zhiqiang Xie Mengqi Xu Yi Zhang Gaoxu Wang EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River Applied Sciences real-time object detection video streaming multi-scale feature |
| title | EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River |
| title_full | EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River |
| title_fullStr | EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River |
| title_full_unstemmed | EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River |
| title_short | EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River |
| title_sort | eyolov3 an efficient real time detection model for floating object on river |
| topic | real-time object detection video streaming multi-scale feature |
| url | https://www.mdpi.com/2076-3417/13/4/2303 |
| work_keys_str_mv | AT lilizhang eyolov3anefficientrealtimedetectionmodelforfloatingobjectonriver AT zhiqiangxie eyolov3anefficientrealtimedetectionmodelforfloatingobjectonriver AT mengqixu eyolov3anefficientrealtimedetectionmodelforfloatingobjectonriver AT yizhang eyolov3anefficientrealtimedetectionmodelforfloatingobjectonriver AT gaoxuwang eyolov3anefficientrealtimedetectionmodelforfloatingobjectonriver |