Yolov4-tiny with wing convolution layer for detecting fish body part

• Published in: Computers and electronics in agriculture 2022-07, Vol.198, p.107023, Article 107023
• Main Authors: Prasetyo, Eko, Suciati, Nanik, Fatichah, Chastine
• Format: Article
• Language: English
• Subjects: Head; Scale detector; Spatial pyramid pooling; Tail and fish detection; Wing convolutional layer; Yolov4-tiny
• ISSN: 0168-1699
• DOI: 10.1016/j.compag.2022.107023

•Determining the freshness and species of fish and calculating the number of fish requires the detection of a fish's eye, tail, and body.•Improving Yolov4-tiny detection accuracy by enhancing and balancing feature diversity and attaching an extra-branch detector to detect small-sized objects.•Enhancing and balancing feature diversity using wing convolutional layer (WCL) and tiny spatial pyramid pooling (Tiny-SPP).•Reducing computational resources of feature pyramid network (FPN) connections using bottleneck and expansion convolution (BEC).•Our proposed model outperforms the original model and other modified Yolov4-tiny models with smaller sizes and more efficient use of computing resources. Detection of a fish's eye, tail and body is the initial process in the vision system for determining the freshness and species of fish, as well as calculating the number of fish automatically in the fishing industry. Classification performance of a system is affected by its ability to detect the intact body of a fish or its body parts. The You Only Look Once version 4 tiny (Yolov4-tiny) is a lightweight object detector that can detect body parts of a fish with fairly good detection accuracy. However, massive siltation of convolution layer in the Yolov4-tiny backbone leads to low feature diversity. This research proposes a modification of the Yolov4-tiny architecture to improve detection accuracy by enhancing and balancing feature diversity and attaching an extra-branch detector to detect small-sized objects. In addition, we propose the use of bottleneck and expansion convolution to reduce computational resources usage. Our contributions are enhancing feature diversity using a wing convolution layer (WCL), balancing feature diversity using tiny spatial pyramid pooling (Tiny-SPP), reducing computational resources of feature pyramid network (FPN) connections using bottleneck and expansion convolution (BEC), and detecting small objects using an extra-branch as a third-scale detector. Our experimental results show that the proposed model outperforms the original model and other modified Yolov4-tiny models with Precision, Recall, AP, and mAP of 97.48%, 93.3%, 94.07%, and 92.38% respectively. The proposed model is smaller in size and more efficient in the use of computing resources.