| 引用本文: | 周孟然a ,范桃春b ,王 宁b ,蔡 睿b.基于改进 YOLOv7 的漂浮垃圾目标检测(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2025，42（4）：72-79 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 目的 针对复杂的内河河道环境,漂浮垃圾中小目标物体占大多数且易受来自水面和岸边环境反光等因素
影响,造成目标外形模糊,易被遮挡,给目标检测带来困难;提出了一种基于改进 YOLOv7 的河道漂浮垃圾检测算
法。 方法 首先,针对河道漂浮垃圾的受环境影响外形发生变化,通过改进 SPPCSPC 模块,增强对小目标物体的特
征提取能力;其次,加入中心化特征金字塔,通过 ROI( region of interest) 与特征金字塔进行加权融合,方便对于不同
尺度目标的检测。 最后,由于针对传统 IoU( intersection over union) 对于小目标物体位置偏差非常敏感,降低了检
测性能。 采用了 Wasserstein Distance 来替代 IoU 作为检测衡量指标,通过引入基于 NWD( Normalized Wasserstein
Distance) 的损失函数,从而提高检测精度。 结果 实验结果表明:改进 YOLOv7 算法模型准确率增加 3. 1% 达到
89. 7%,并在 IoU 为 0. 5 以及 IoU 在 0. 5 ~ 0. 95 情况下,平均均值精度分别增加了 6%、4. 6%,分别达到 87. 8%、
43. 4%,检测结果优于其他经典检测模型。 结论 通过实验结果可以看出,改进后模型在检测精度上有显著提升,对
于实际应用具有一定的参考价值。 |
| 关键词: YOLOv7 小目标检测 EVC Block SPPCSPC NWD |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Floating Garbage Object Detection Based on Improved YOLOv7 |
|
ZHOU Mengrana FAN Taochunb WANG Ningb CAI Ruib
|
|
a. School of Electrical and Information Engineering b. School of Mechanics and Optoelectronic Physics Anhui University
of Science and Technology Anhui Huainan 232001 China
|
| Abstract: |
| Objective In complex inland river environments most floating garbage consists of small targets that are easily
affected by reflections from the water surface and riverbanks. This results in blurred and obstructed target shapes which
poses significant challenges for target detection. To address this issue this paper proposed an improved YOLOv7-based
algorithm for detecting floating garbage in rivers. Methods Firstly to address the morphological variations of floating
garbage in river environments caused by environmental factors the feature extraction capabilities for small targets were
enhanced through the refinement of the SPPCSPC module. Secondly the centralized feature pyramid was added which
was weighted and fused with the feature pyramid through ROI region of interest to facilitate the detection of targets at
different scales. Finally given that traditional Intersection over Union IoU is highly sensitive to positional deviations of
small targets which reduces detection performance IoU was replaced with Wasserstein Distance as the evaluation metric. A loss function based on Normalized Wasserstein Distance NWD was implemented to improve detection accuracy.
Results The experimental results showed that the accuracy of the improved YOLOv7 algorithm model increased by 3. 1%
reaching 89. 7%. At IoU = 0. 5 the average mean precision increased by 6% reaching 87. 8% and for IoU ranging from
0. 5 to 0. 95 the average mean precision increased by 4. 6% reaching 43. 4%. The detection results of this improved
model outperform those of other classical detection models. Conclusion The experimental results indicate that the
improved model significantly enhances detection accuracy providing valuable insights for practical applications. |
| Key words: YOLOv7 small object detection EVC block SPPCSPC NWD |
