YOLO-CCA通过融合局部与全局上下文，提升交通标志检测精度并减少参数量。
YOLO-CCA: A Context-Based Approach for Traffic Sign Detection
- 引入多尺度空洞卷积增强局部上下文特征，捕捉目标与周围关系。
- 设计全局上下文提取模块，从整图获取关键位置信息，提升定位能力。
- 基于Transformer的上下文融合模块实现高效多级特征整合，适合嵌入式部署。
交通标志检测对提升道路安全和推动自动驾驶技术至关重要。由于驾驶环境复杂，检测常面临低分辨率、特征信息有限和小目标等问题，导致特征提取困难，出现误检和漏检。为此，本文提出一种基于上下文的交通标志检测方法，以YOLOv7为基础模型。首先，提出自适应局部上下文特征增强（LCFE）模块，利用多尺度空洞卷积捕获目标与周边区域的潜在关联，补充局部上下文信息。其次，提出全局上下文特征采集（GCFC）模块，从整个图像场景中提取关键位置特征作为全局上下文。最后，构建基于Transformer的上下文收集增强（CCA）模块，处理融合后的局部与全局上下文，实现对YOLOv7的优越多层级特征融合，且不增加额外计算负担。在清华大学-腾讯100K数据集上的实验表明，该方法mAP达92.1%，较YOLOv7提升3.9%，参数量减少2.7M；在CCTSDB2021数据集上mAP提升0.9%。结果表明，该方法在提高检测精度的同时降低参数量。源代码见https://github.com/zippiest/yolo-cca。
原文摘要 · Abstract (English)
Traffic sign detection is crucial for improving road safety and advancing autonomous driving technologies. Due to the complexity of driving environments, traffic sign detection frequently encounters a range of challenges, including low resolution, limited feature information, and small object sizes. These challenges significantly hinder the effective extraction of features from traffic signs, resulting in false positives and false negatives in object detection. To address these challenges, it is essential to explore more efficient and accurate approaches for traffic sign detection. This paper proposes a context-based algorithm for traffic sign detection, which utilizes YOLOv7 as the baseline model. Firstly, we propose an adaptive local context feature enhancement (LCFE) module using multi-scale dilation convolution to capture potential relationships between the object and surrounding areas. This module supplements the network with additional local context information. Secondly, we propose a global context feature collection (GCFC) module to extract key location features from the entire image scene as global context information. Finally, we build a Transformer-based context collection augmentation (CCA) module to process the collected local context and global context, which achieves superior multi-level feature fusion results for YOLOv7 without bringing in additional complexity. Extensive experimental studies performed on the Tsinghua-Tencent 100K dataset show that the mAP of our method is 92.1\%. Compared with YOLOv7, our approach improves 3.9\% in mAP, while the amount of parameters is reduced by 2.7M. On the CCTSDB2021 dataset the mAP is improved by 0.9\%. These results show that our approach achieves higher detection accuracy with fewer parameters. The source code is available at \url{https://github.com/zippiest/yolo-cca}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。