Tunnel-YOLO: A New Traffic Vehicle Detection Method Using Feature Enhancement for Complex Tunnel Environments

Vision-based traffic sign detection plays a crucial role in intelligent transportation systems. Recently, many approaches based on deep learning for traffic sign detection have been proposed and showed better performance compared with traditional approaches. However, due to difficult conditions in driving environment and the size of traffic signs in traffic scene images, the performance of deep learning-based methods on small traffic sign detection is still limited. In addition, the inference speed of current state-of-the-art approaches on traffic sign detection is still slow. This paper proposes a deep learning-based approach to improve the performance of small traffic sign detection in driving environments. First, a lightweight and efficient architecture is adopted as the base network to address the issue of the inference speed. To enhance the performance on small traffic sign detection, a deconvolution module is adopted to generate an enhanced feature map by aggregating a lower-level feature map with a higher-level feature map. Then, two improved region proposal networks are used to generate proposals from the highest-level feature map and the enhanced feature map. The proposed improved region proposal network is designed for fast and accuracy proposal generation. In the experiments, the German Traffic Sign Detection Benchmark dataset is used to evaluate the effectiveness of each enhanced module, and the Tsinghua-Tencent 100K dataset is used to compare the effectiveness of the proposed approach with other state-of-the-art approaches on traffic sign detection. Experimental results on Tsinghua-Tencent 100K dataset show that the proposed approach achieves competitive performance compared with current state-of-the-art approaches on traffic sign detection while being faster and simpler.

Object detection for vehicles and pedestrians is extremely difficult to achieve in autopilot applications for the Internet of vehicles, and it is a task that requires the ability to locate and identify smaller targets even in complex environments. This paper proposes a single-stage object detection network (YOLOv3-promote) for the detection of vehicles and pedestrians in complex environments in cities, which improves on the traditional You Only Look Once version 3 (YOLOv3). First, spatial pyramid pooling is used to fuse local and global features in an image to better enrich the expression ability of the feature map and to more effectively detect targets with large size differences in the image; second, an attention mechanism is added to the feature map to weight each channel, thereby enhancing key features and removing redundant features, which allows for strengthening the ability of the feature network to discriminate between target objects and backgrounds; lastly, the anchor box derived from the K-means clustering algorithm is fitted to the final prediction box to complete the positioning and identification of target vehicles and pedestrians. The experimental results show that the proposed method achieved 91.4 mAP (mean average precision), 83.2 F1 score, and 43.7 frames per second (FPS) on the KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) dataset, and the detection performance was superior to the conventional YOLOv3 algorithm in terms of both accuracy and speed.

Aiming at the problems of low detection and tracking accuracy, poor robustness and inaccurate vehicle flow statistics of multi-vehicle types in surveillance video, an artificial intelligence-based vehicle detection and tracking method was proposed. This method reconstructed the feature extraction network of the target detection model YOLOv5s to enhance the extraction of important features of the target and improve the detection accuracy of the detector. Firstly, Swin Transformer module is introduced into the Backbone network to replace part of C3 modules in the original algorithm, so as to enhance the global modeling ability of the model, better capture the context feature information, and expand the model's receptive field. Then, by comparing different attention mechanisms, NAM attention is selected to access the Neck network to enhance the cross-dimensional interaction between the channel and spatial dimensions of information, reduce information loss and enhance the performance of the network. Finally, the feature extraction network part of the DeepSort algorithm was optimized and retrained on the vehicle rerecognition data set to make it more suitable for vehicle tracking. The experimental results show that the accuracy of vehicle detection by the improved YOLOv5s is increased by 1.93 percentage points compared with the original algorithm. Combined with the DeepSort algorithm, the accuracy of vehicle flow statistics under different lighting conditions such as daytime, evening and night can reach 97.2%, 97.5% and 80.4% respectively.

Traffic light detection and recognition are crucial for enhancing the security of unmanned systems. This study proposes a YOLOv5-based traffic light-detection algorithm to tackle the challenges posed by small targets and complex urban backgrounds. Initially, the Mosaic-9 method is employed to enhance the training dataset, thereby boosting the network’s ability to generalize and adapt to real-world scenarios. Furthermore, the Squeeze-and-Excitation (SE) attention mechanism is incorporated to improve the network. Moreover, the YOLOv5 algorithm’s loss function is optimized by substituting it with Efficient Intersection over Union loss (EIoU_loss), which addresses issues like missed detection and false alarms. Experimental results demonstrate that the model trained with this enhanced network achieves an mAP (mean average precision) of 99.4% on a custom dataset, which is 6.3% higher than that of the original YOLOv5, while maintaining a detection speed of 74 f/s. Therefore, this algorithm offers higher detection accuracy and effectively meets real-time operational requirements. The proposed method has a strong application potential, and can be widely used in the field of automatic driving, assisted driving, etc. Its application is not only of great significance in improving the accuracy and speed of traffic sign detection, but also can provide technical support for the development of intelligent transportation systems.

With advancements in autonomous driving, demand for stringent and computationally efficient traffic sign detection systems has increased. However, bringing such a system to a deployable level requires handling critical accuracy and processing speed issues. A focal loss-based single-stage object detector, i.e RetinaNet, is used as a trade-off between accuracy and processing speed as it handles the class imbalance problem of the single-stage detector and is thus suitable for traffic sign detection (TSD). We assessed the detector’s performance by combining various feature extractors such as ResNet-50, ResNet-101, and ResNet-152 on three publicly available TSD benchmark datasets. Performance comparison of the detector using different backbone includes evaluation parameters like mean average precision (mAP), memory allocation, running time, and floating-point operations. From the evaluation results, we found that the RetinaNet object detector using the ResNet-152 backbone obtains the best mAP, while that using ResNet-101 strikes the best trade-off between accuracy and execution time. The motivation behind benchmarking the detector on different datasets is to analyse the detector’s performance on different TSD benchmark datasets. Among the three feature extractors, the RetinaNet model trained using the ResNet-50 backbone is an excellent model in memory consumption, making it an optimal choice for low-cost embedded devices deployment.

In the current scenario on the increasing number of motor vehicles day by day, so traffic regulation faces many challenges on intelligent road surveillance and governance, this is one of the important research areas in the artificial intelligence or deep learning. Among various technologies, computer vision and machine learning algorithms have the most efficient, as a huge vehicles video or image data on road is available for study. In this paper, we proposed computer vision-based an efficient approach to vehicle detection, recognition and Tracking. We merge with one-stage (YOLOv4) and two-stage (R-FCN) detectors methods to improve vehicle detection accuracy and speed results. Two-stage object detection methods provide high localization and object recognition precision, even as one-stage detectors achieve high inference and test speed. Deep-SORT tracker method applied for detects bounding boxes to estimate trajectories. We analyze the performance of the Mask RCNN benchmark, YOLOv3 and Proposed YOLOv4 + R-FCN on the UA-DETRAC dataset and study with certain parameters like Mean Average Precisions (mAP), Precision recall.

Traffic sign detection is crucial in intelligent transportation and assisted driving, providing favourable support for driving safety and prevention of traffic accidents. Aiming at the current traffic sign detection problems of leakage, misdetection and low detection accuracy of small targets, a traffic sign detection method based on improved YOLOv8n is proposed. Firstly, the Neck part of YOLOv8 is improved by designing a module that combines Attention Scale Sequence Fusion with the P2 small target detection layer (AFP) to enhance the feature extraction capability of the YOLOv8 network, enabling it to capture more small target features. Secondly, a lightweight convolution module, LWConv, is designed, based on which the Bottleneck structure of Cross-convolution with two filters (C2f) in YOLOv8 is reconstructed and named LW_C2f, effectively reducing the model size and parameters. Finally, the loss function of the original YOLOv8 is replaced with the Wise-IoU loss function, which improves the network’s bounding box regression performance and reduces the negative impact of low-quality samples. The experimental results show that the mean average precision (mAP50) of the improved model on the TT100K dataset is increased by 5.7% compared to the YOLOv8 model, while the number of parameters and the model size are reduced by 0.6 M and 0.8 MB, respectively.

Due to the dramatical grow of road transport, Advanced Driver Assistance Systems (ADAS) are being one of the most popular system. The main challenge of these systems is to improve driving safety and reduce accidents. Robust and effective vehicle detection is a critical step. However, vehicle detection meets many difficulties such as complex background, different size, model and orientations of vehicle. To solve this problem, this paper introduces an approach for traffic vehicle detection based on multi-scale covariance descriptor (MSCOV) for the image description and support vector machine classifier (SVM) for the data classification. This method is evaluated and compared to existing detection approach. The result of this approach outperforms existing vehicle detection system using the same dataset.

To realize road traffic flow surveillance under various environments which contain poor visibility conditions, we have already proposed two vehicle detection methods using thermal images taken with an infrared thermal camera. The first method uses pattern recognition for the windshields and their surroundings to detect vehicles. However, the first method decreases the vehicle detection accuracy in winter season. To maintain high vehicle detection accuracy in all seasons, we developed the second method. The second method uses tires' thermal energy reflection areas on a road as the detection targets. The second method did not achieve high detection accuracy for vehicles on left-hand and right-hand lanes except for two center-lanes. Therefore, we have developed a new method based on the second method to increase the vehicle detection accuracy. This paper proposes the new method and shows that the detection accuracy for vehicles on all lanes is 92.1%. Therefore, by combining the first method and the new method, high vehicle detection accuracies are maintained under various environments, and road traffic flow surveillance can be realized.

The traditional traffic sign detection algorithm can not deal with the application scenarios such as intelligent transportation system or advanced assisted driving environment, and it is difficult to meet the application requirements in detection accuracy and efficiency. Focusing on the above problems, this paper proposes a traffic sign detection algorithm based on Single Shot Multibox Detector (SSD) combined with Receptive Field Module (RFM) and Path Aggregation Network (PAN). The proposed algorithm is abbreviated to SSD-RP. The SSD-RP uses the RFM to improve the receptive field and semantics of the predicted feature maps, thus improving the detection performance of small traffic signs. At the same time, the path aggregation network is introduced to integrate multiscale features, which makes the abstract semantic information and rich detailed information shared among multiscale feature maps, enhances the discrimination ability of feature system, and improves the location and classification accuracy of traffic signs. Following that, the spatial pyramid pooling module is used to pool the shallow features and integrate them into the bottom-up information transmission path of the path aggregation network, thus continuing to supplement the fine-grained features for the feature system and further improve the detection performance. The experimental results on GTSDB and CCTSDB data sets show that SSD-RP has higher mean average precision (mAP) than traditional SSD algorithm and can better detect small traffic signs, which means that SSD-RP has higher detection precision. In addition, the experimental results also show that, compared with the common object detection algorithms such as Faster R-CNN, RetinaNet, and YOLOv3, the SSD-RP achieves a better balance between detection time and detection precision.

In the field of intelligent transportation, accurate vehicle detection, tracking, and re-identification are essential tasks that enable real-time monitoring, congestion management, and safety improvements. To address these needs in high-traffic highway environments, this study proposes a multi stage traffic flow model combining deep learning and metric learning. The model leverages the Segment Anything Model for vehicle detection, utilizing language-prompting to automate segmentation, thereby reducing manual adjustments and improving adaptability across complex traffic scenarios. For vehicle tracking, the model employs the StrongSORT algorithm, integrated with mask-based tracking to enhance recognition coherence and maintain resilience against occlusions, especially in congested conditions. Additionally, the PP-OCR module accurately extracts timestamps to support interval speed measurement across multiple viewpoints, using vehicle re-identification results for precise multi-camera tracking. Experimental results demonstrate that the proposed model significantly outperforms state-of-the-art methods, achieving higher mean average precision and tracking accuracy in both high-density and challenging traffic conditions, highlighting its robustness and suitability for intelligent transportation systems.

Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type recognition, low detection accuracy, and slow speed, a new vehicle detection model YOLOv2_Vehicle based on YOLOv2 is proposed in this paper. The k-means++ clustering algorithm was used to cluster the vehicle bounding boxes on the training dataset, and six anchor boxes with different sizes were selected. Considering that the different scales of the vehicles may influence the vehicle detection model, normalization was applied to improve the loss calculation method for length and width of bounding boxes. To improve the feature extraction ability of the network, the multi-layer feature fusion strategy was adopted, and the repeated convolution layers in high layers were removed. The experimental results on the Beijing Institute of Technology (BIT)-Vehicle validation dataset demonstrated that the mean Average Precision (mAP) could reach 94.78%. The proposed model also showed excellent generalization ability on the CompCars test dataset, where the “vehicle face” is quite different from the training dataset. With the comparison experiments, it was proven that the proposed method is effective for vehicle detection. In addition, with network visualization, the proposed model showed excellent feature extraction ability.

With the potential to increase road safety and provide economic benefits, intelligent vehicles have elicited a significant amount of interest from both academics and industry. A robust and reliable vehicle detection and tracking system is one of the key modules for intelligent vehicles to perceive the surrounding environment. The millimeter-wave radar and the monocular camera are two vehicular sensors commonly used for vehicle detection and tracking. Despite their advantages, the drawbacks of these two sensors make them insufficient when used separately. Thus, the fusion of these two sensors is considered as an efficient way to address the challenge. This paper presents a collaborative fusion approach to achieve the optimal balance between vehicle detection accuracy and computational efficiency. The proposed vehicle detection and tracking design is extensively evaluated with a real-world data set collected by the developed intelligent vehicle. Experimental results show that the proposed system can detect on-road vehicles with 92.36% detection rate and 0% false alarm rate, and it only takes ten frames (0.16 s) for the detection and tracking of each vehicle. This system is installed on Kuafu-II intelligent vehicle for the fourth and fifth autonomous vehicle competitions, which is called “Intelligent Vehicle Future Challenge” in China.

<p>In this work, the focus was on the YOLO model and the features of its work. Tests and comparisons with other state-of-the-art were given, which show that YOLO is the fastest model for real time objects recognition today. The architecture of the algorithm and the essential components on which the field experiment was conducted are described. Based on the results obtained, it was concluded that the YOLOv4 recognition model shows excellent results in terms of accuracy and speed</p>

Traditional traffic light detection systems rely on handcrafted features and classical machine learning algorithms. Accurately detecting traffic lights amidst the complexities of real-world traffic scenarios presents formidable challenges. This paper enhances YOLOv8 for accurate and efficient traffic light detection. A Dual Attention Network (DUANet) integrates into the backbone for improved feature representation. A Spatial Pyramid Pooling Cross-Stage Partial Connection (SPPCSPC) layer in the neck handles varying input sizes. The integration of DUANet facilitates the capture of both channel-wise and spatial dependencies within feature maps, enhancing feature representation and enabling more accurate traffic light localization. DUA-YOLOv8 outperforms the baseline YOLOv8 model, achieving an impressive mean Average Precision (mAP) of 0.995 % while maintaining real-time inference speeds of 55.248 frames per second (FPS). Comparative analysis against existing methods further validates the superiority of our approach, particularly in complex traffic scenarios. Our study contributes to the advancement of autonomous driving technology by addressing the critical task of traffic light detection.