The quantification of fishing information on fishing vessels is a prerequisite for implementing refined management of quota-based fishing. In order to address the target detection and information quantification issues in the quota-based fishing of , this study installed an Electronic Monitoring (EM) system on fishing vessels. Using the EM system video as a data source. Based on YOLOv7, an improved object detection algorithm (YOLOv7-DCN) is proposed. Additionally, drawing on the main ideas of the SORT algorithm, a target counting algorithm is also proposed (YOLOv7-DCN-SORT). YOLOv7-DCN object detection algorithm uses DCNv2 as the backbone network to detect the main targets in fishing vessel operations, improving the network's ability to detect deformable targets. The YOLOv7-DCN-SORT target counting algorithm utilizes the YOLOv7-DCN obtained in the detection phase as the target detection model. It applies the Kalman filter and Hungarian algorithm from the SORT algorithm to track and predict the counted targets. By setting collision detection lines, timestamps, thresholds, and counters, this algorithm can accurately count the number of baskets filled with and the number of nets deployed during fishing operations. The results show that: 1) The improved YOLOv7-DCN achieved precision, recall, mAP, and F1-score of 98.21%, 98.43%, 99.19%, and 98.33%, respectively, for each target detection category on the test set. These values represent improvements of 2.06%, 0.64%, 0.08%, and 1.37% compared to the original YOLOv7 model. 2) The YOLOv7-DCN-SORT algorithm achieved counting accuracy rates of 82.00% for counting the number of baskets and 96.61% for the number of deployed nets. In summary, this study provides methods for automated recording and intelligent information processing in operations on offshore fishing vessels, serving as a reference for quota-based fishing management decisions.

中文翻译：

---

YOLOv7-DCN-SORT：一种用于在 Acetes 渔船作业中检测和计数目标的算法

渔船捕捞信息量化是实施配额捕捞精细化管理的前提。为了解决配额捕捞中的目标检测和信息量化问题，本研究在渔船上安装了电子监控（EM）系统。使用EM系统视频作为数据源。基于YOLOv7，提出一种改进的目标检测算法（YOLOv7-DCN）。此外，借鉴SORT算法的主要思想，还提出了目标计数算法（YOLOv7-DCN-SORT）。 YOLOv7-DCN目标检测算法以DCNv2为骨干网络，对渔船作业中的主要目标进行检测，提高了网络对变形目标的检测能力。 YOLOv7-DCN-SORT目标计数算法利用检测阶段获得的YOLOv7-DCN作为目标检测模型。它应用 SORT 算法中的卡尔曼滤波器和匈牙利算法来跟踪和预测计数的目标。该算法通过设置碰撞检测线、时间戳、阈值和计数器，可以准确统计捕捞作业过程中的装篮数量和撒网数量。结果表明：1）改进后的YOLOv7-DCN在测试集上每个目标检测类别的精度、召回率、mAP和F1分数分别为98.21%、98.43%、99.19%和98.33%。与原始 YOLOv7 模型相比，这些值分别提高了 2.06%、0.64%、0.08% 和 1.37%。 2）YOLOv7-DCN-SORT算法的篮子数量计数准确率达到82.00%，部署网络数量计数准确率达到96.61%。综上所述，本研究为近海渔船作业过程中的自动化记录和智能信息处理提供了方法，为基于配额的捕捞管理决策提供参考。