MMD-YOLOv7:黑暗条件下车辆检测方法

doi:10.19678/j.issn.1000-3428.0069139

摘要/Abstract

摘要：

车辆检测与识别是智能交通和自动驾驶领域的一项关键技术, 对于道路安全和自动驾驶起着至关重要的作用, 一直是备受关注的研究热点。基于深度学习的目标检测模型, 使得车辆检测精度得到大幅提高, 但在夜间低光照和恶劣天气等不利条件下现有车辆检测技术的精度和可靠性仍然存在极大挑战。针对这一问题, 基于YOLOv7模型, 提出一种针对夜间黑暗条件下的车辆检测方法MMD-YOLOv7。首先基于坐标注意力(CA)机制构建一种新的多通道坐标注意力(MCCA)模块, 显著提升模型在捕捉全局和局部特征信息方面的能力。其次通过构建一个多尺度卷积(MSC)模块实现对扩展高效层聚合网络(ELAN)结构的针对性改进, 使得模型更好地适应夜间视觉环境中的噪声干扰, 同时提升了特征提取的能力和精度。最后, 引入了多分支模块(DBB), 进一步增强模型对复杂特征的捕捉能力。为了验证所提出的模型效果, 选取了BDD100K数据集中的6 000张夜间场景图片进行训练和测试, 实验结果表明, 该模型在车辆检测精度上相比原始YOLOv7模型提升了5.3百分点, 展现出了模型在处理低光照情况下的强大能力。此外, 在其他多个公开的车辆检测数据集上也表现出了很好的性能, 验证了该模型具备很强的鲁棒性和泛化能力。

关键词: YOLO模型, 目标检测, 车辆检测, 深度学习, 注意力机制

Abstract:

Vehicle detection and identification is a key technology in the field of intelligent transportation and autonomous driving. It plays a vital role in road safety and autonomous driving and has always been a research hotspot. Target detection models based on deep learning have greatly improved vehicle detection accuracy, but challenges related to the accuracy and reliability of existing vehicle detection technology under adverse conditions, such as low light at night and bad weather, remain. To address these challenges, a vehicle detection method and model specifically targeted at nighttime dark conditions-MMD-YOLOv7-is proposed based on the YOLOv7 model. First, a new Multi-Channel Coordinate Attention (MCCA) module is constructed based on the Coordinate Attention (CA) mechanism, which significantly improves the model's ability to capture global and local feature information. Second, a Multi-Scale Convolution (MSC) module is innovatively designed and constructed to achieve targeted improvements to the Efficient Layer Aggregation Networks (ELAN) structure, allowing the model to better adapt to noise interference in the night visual environment, while improving the capability and accuracy of feature extraction. Finally, the Diverse Branch Block (DBB) is introduced to further enhance the model's ability to capture complex features. To verify the effectiveness of the proposed model, 6 000 night scene images in the BDD100K dataset are selected for training and testing. The experimental results show that the proposed model's vehicle detection accuracy is improved by 5.3 percentage points compared to the original YOLOv7 model, indicating its strong ability to handle low light conditions. In addition, it shows good performance on multiple public vehicle detection datasets, verifying its strong robustness and generalization capabilities.

Key words: YOLO model, target detection, vehicle detection, deep learning, attention mechanism

黄金贵, 刘朋, 唐文胜. MMD-YOLOv7:黑暗条件下车辆检测方法[J]. 计算机工程, 2025, 51(9): 340-349.

HUANG Jingui, LIU Peng, TANG Wensheng. MMD-YOLOv7: Vehicle Detection Method Under Dark Conditions[J]. Computer Engineering, 2025, 51(9): 340-349.

https://www.ecice06.com/CN/Y2025/V51/I9/340

图/表 14

图1 YOLOv7模型的结构

Fig.1 Structure of the YOLOv7 model

图2 MMD-YOLOv7模型的结构

Fig.2 The structure of MMD-YOLOv7 model

图3 MCCA模块结构

Fig.3 The structure of MCCA module

图4 MSC模块结构

Fig.4 The structure of MSC module

图5 ELAN模块和ELAN_MSC模块的结构

Fig.5 The structure of ELAN module and ELAN_MSC module

图6 DBB模块结构

Fig.6 The structure of DBB module

图7 MP模块和MP_DBB模块的结构

Fig.7 The structure of MP module and MP_DBB module

图8 在BBD数据集上的检测结果对比

Fig.8 Comparison of detection results on BBD dataset

图9 在多种场景下的检测结果对比

Fig.9 Comparison of detection results in various scenarios

参考文献 26

1	WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7464-7475.
2	HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 13713-13722.
3	DING X H, ZHANG X Y, HAN J G, et al. Diverse branch block: building a convolution as an inception-like unit[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 10886-10895.
4	YU F, CHEN H F, WANG X, et al. BDD100K: a diverse driving dataset for heterogeneous multitask learning[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 2636-2645.
5	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2014: 580-587.
6	GIRSHICK R. Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2015: 1440-1448.
7	REN S , HE K , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
8	HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2961-2969.
9	TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 10781-10790.
10	LIU W , ANGUELOV D , ERHAN D , et al. SSD: single shot MultiBox detector. Berlin, Germany: Springer, 2016.
11	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2980-2988.
12	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2017: 7263-7271.
13	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-11-20]. https://arxiv.org/abs/1804.02767v1.
14	CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 213-229.
15	HNEWA M, RADHA H. Object detection under rainy conditions for autonomous vehicles: a review of state-of-the-art and emerging techniques[EB/OL]. [2023-11-20]. https://arxiv.org/abs/2006.16471v4.
16	NABATI R, QI H R. RRPN: radar region proposal network for object detection in autonomous vehicles[C]//Proceedings of IEEE International Conference on Image Processing. Washington D. C., USA: IEEE Press, 2019: 3093-3097.
17	CARRANZA-GARCÍA M , TORRES-MATEO J , LARA-BENÍTEZ P , et al. On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data. Remote Sensing, 2021, 13 (1): 89.
18	BENJUMEA A, TEETI I, CUZZOLIN F, et al. YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles[EB/OL]. [2023-11-20]. https://arxiv.org/abs/2112.11798v4.
19	刘航博, 马礼, 李阳, 等. 无人驾驶中运用DQN进行障碍物分类的避障方法. 计算机工程, 2024, 50 (11): 380- 389. doi: 10.19678/j.issn.1000-3428.0068769
	LIU H B , MA L , LI Y , et al. An obstacle avoidance method using DQN to classify obstacles in unmanned driving. Computer Engineering, 2024, 50 (11): 380- 389. doi: 10.19678/j.issn.1000-3428.0068769
20	李松江, 耿兰兰, 王鹏. 基于改进Yolov4的车辆目标检测. 计算机工程, 2023, 49 (4): 272- 280. doi: 10.19678/j.issn.1000-3428.0062943
	LI S J , GENG L L , WANG P . Vehicle target detection based on improved Yolov4. Computer Engineering, 2023, 49 (4): 272- 280. doi: 10.19678/j.issn.1000-3428.0062943
21	谢竞, 邓月明, 王润民. 改进YOLOv8s的交通标识检测算法. 计算机工程, 2024, 40 (11): 338- 349. doi: 10.19678/j.issn.1000-3428.0068742
	XIE J , DENG Y M , WANG R M . Improved YOLOv8s traffic sign detection algorithm. Computer Engineering, 2024, 40 (11): 338- 349. doi: 10.19678/j.issn.1000-3428.0068742
22	杨秀娟, 曾智勇. 基于YOLOv5的无人机航拍改进目标检测算法Dy-YOLO. 福建师范大学学报(自然科学版), 2024, 40 (1): 76- 86.
	YANG X J , ZENG Z Y . Improved target detection algorithm Dy-YOLO for UAV aerial photography based on YOLOv5. Journal of Fujian Normal University(Natural Science Edition), 2024, 40 (1): 76- 86.
23	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2017: 2117-2125.
24	WEN L Y , DU D W , CAI Z W , et al. UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Computer Vision and Image Understanding, 2020, 193, 102907.
25	DONG Z , WU Y W , PEI M T , et al. Vehicle type classification using a semisupervised convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 2020, 16 (4): 2247- 2256.
26	ZHU P F, WEN L Y, BIAN X, et al. Vision meets drones: a challenge[EB/OL]. [2023-11-20]. https://arxiv.org/abs/1804.07437v2.

[1]	符家成, 田瑾, 张玉金, 方志军. 结合前置三元组集的知识图谱推荐[J]. 计算机工程, 2025, 51(9): 101-109.
[2]	周晨阳, 刘雪宇, 梁少华, 吴永飞. 基于Swin Transformer的肾动脉血管检测分割与定量分析[J]. 计算机工程, 2025, 51(9): 252-267.
[3]	翟志鹏, 曹阳, 沈琴琴, 施佺. 基于多时空图融合与动态注意力的交通流预测[J]. 计算机工程, 2025, 51(9): 139-148.
[4]	王舒梦, 徐慧英, 朱信忠, 黄晓, 宋杰, 李毅. 基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO[J]. 计算机工程, 2025, 51(9): 280-293.
[5]	朱思远, 李佳圣, 邹丹平, 何迪, 郁文贤. 基于半监督学习的非结构化道路缺陷检测算法[J]. 计算机工程, 2025, 51(9): 14-24.
[6]	徐瀅, 傅紫薇, 张伟, 陈云芳. 基于抽象语法树嵌入的智能合约漏洞检测技术[J]. 计算机工程, 2025, 51(9): 149-157.
[7]	马淦, 谷雨, 彭冬亮. 结合改进YOLOv5s和动态数据增强的海面舰船检测[J]. 计算机工程, 2025, 51(9): 294-305.
[8]	陈彦如, 刘珂良, 冉茂亮. 基于深度强化学习的外卖即时配送实时优化[J]. 计算机工程, 2025, 51(9): 328-339.
[9]	林帆, 李建华. 基于多阶门控聚合网络的光学化学结构识别[J]. 计算机工程, 2025, 51(8): 364-372.
[10]	苗茹, 李祎, 周珂, 张俨娜, 常然然, 孟更. 一种改进的Faster R-CNN遥感图像多目标检测模型研究[J]. 计算机工程, 2025, 51(8): 292-304.
[11]	武东辉, 王金凤, 仇森, 刘国志. 基于EWBiLSTM-ATT的数据手套手语识别[J]. 计算机工程, 2025, 51(8): 107-119.
[12]	倪源松, 韩军, 邹小燕, 胡广怡, 王文帅. 两阶段自适应分块输电线路螺栓缺陷检测方法[J]. 计算机工程, 2025, 51(8): 281-291.
[13]	郝宏达, 罗健旭. 基于多尺度区域特征融合的多器官语义分割模型[J]. 计算机工程, 2025, 51(8): 270-280.
[14]	武东辉, 王金凤, 仇森, 刘国志. 基于EWBiLSTM-ATT的数据手套手语识别[J]. 计算机工程, 2025, 51(8): 107-119.
[15]	张昭理, 李家豪, 刘海, 石佛波, 何嘉文. 基于个性化遗忘建模的知识追踪方法[J]. 计算机工程, 2025, 51(8): 120-130.

选择文件类型/文献管理软件名称

选择包含的内容