Object detection in road scenes is a task that has recently become popular and it is also an important part of intelligent transportation systems. Due to the different locations of cameras in the road scenes, the size of the traffic objects captured varies greatly, which imposes a burden on the network optimization. In addition, in some dense traffic scenes, the size of the traffic objects captured is extremely small and it is easy to miss detection and to encounter false detection. In this paper, we propose an improved multi-scale YOLOv5s algorithm based on the YOLOv5s algorithm. In detail, we add a detection head for extremely small objects to the original YOLOv5s model, which significantly improves the accuracy in detecting extremely small traffic objects. A content-aware reassembly of features (CARAFE) module is introduced in the feature fusion part to enhance the feature fusion. A new SPD-Conv CNN Module is introduced instead of the original convolutional structure to enhance the overall computational efficiency of the model. Finally, the normalization-based attention module (NAM) is introduced, allowing the model to focus on more useful information during training and significantly improving detection accuracy. The experimental results demonstrate that compared with the original YOLOv5s algorithm, the detection accuracy of the multi-scale YOLOv5s model proposed in this paper is improved by 7.1% on the constructed diverse traffic scene datasets. The improved multi-scale YOLOv5s algorithm also maintains the highest detection accuracy among the current mainstream object detection algorithms and is superior in accomplishing the task of detecting traffic objects in complex road scenes.

In order to address the issue of environmental perception in autonomous driving on structured roads, we propose MultiNet-GS, a convolutional neural network model based on an encoder–decoder architecture that tackles multiple tasks simultaneously. We use the main structure of the latest object detection model, the YOLOv8 model, as the encoder structure of our model. We introduce a new dynamic sparse attention mechanism, BiFormer, in the feature extraction part of the model to achieve more flexible computing resource allocation, which can significantly improve the computational efficiency and occupy a small computational overhead. We introduce a lightweight convolution, GSConv, in the feature fusion part of the network, which is used to build the neck part into a new slim-neck structure so as to reduce the computational complexity and inference time of the detector. We also add an additional detector for tiny objects to the conventional three-head detector structure. Finally, we introduce a lane detection method based on guide lines in the lane detection part, which can aggregate the lane feature information into multiple key points, obtain the lane heat map response through conditional convolution, and then describe the lane line through the adaptive decoder, which effectively makes up for the shortcomings of the traditional lane detection method. Our comparative experiments on the BDD100K dataset on the embedded platform NVIDIA Jetson TX2 show that compared with SOTA(YOLOPv2), the mAP@0.5 of the model in traffic object detection reaches 82.1%, which is increased by 2.7%. The accuracy of the model in drivable area detection reaches 93.2%, which is increased by 0.5%. The accuracy of the model in lane detection reaches 85.7%, which is increased by 4.3%. The Params and FLOPs of the model reach 47.5 M and 117.5, which are reduced by 6.6 M and 8.3, respectively. The model achieves 72 FPS, which is increased by 5. Our MultiNet-GS model has the highest detection accuracy among the current mainstream models while maintaining a good detection speed and has certain superiority.