Search

Accurate and rapid response in complex driving scenarios is a challenging problem in autonomous driving. If a target is detected, the vehicle will not be able to react in time, resulting in fatal safety accidents. Therefore, the application of driver assistance systems requires a model that can accurately detect targets in complex scenes and respond quickly. In this paper, a lightweight feature extraction model, ShuffDet, is proposed to replace the CSPDark53 model used by YOLOX by improving the YOLOX algorithm. At the same time, an attention mechanism is introduced into the path aggregation feature pyramid network (PAFPN) to make the network focus more on important information in the network, thereby improving the accuracy of the model. This model, which combines two methods, is called ShuffYOLOX, and it can improve the accuracy of the model while keeping it lightweight. The performance of the ShuffYOLOX model on the KITTI dataset is tested in this paper, and the experimental results show that compared to the original network, the mean average precision (mAP) of the ShuffYOLOX model on the KITTI dataset reaches 92.20%. In addition, the number of parameters of the ShuffYOLOX model is reduced by 34.57%, the Gflops are reduced by 42.19%, and the FPS is increased by 65%. Therefore, the ShuffYOLOX model is very suitable for autonomous driving applications. [ABSTRACT FROM AUTHOR]

3D object detection, as an essential part of perception, plays a principal role in the autonomous driving system. The cost-competitive monocular 3D object detection has drawn increasing attention recently. However, it still suffers an inferior accuracy especially for occluded objects due to the limited camera view. Inspired by compositional models, in which an object is represented as a combination of multiple components, this paper proposes a new monocular 3D object detection method that decreases the impact of occlusion by utilizing an object's front and side cues. To do this, the features are extracted from a decoupled front and side representation and then fused by an attention-based module to obtain a more consistent feature distribution. An uncertainty-guided depth ensemble based on geometry is further applied to refine the depth prediction. Experiment results demonstrate that as compared to the conventional methods, the proposed method significantly improves the detection performance for occluded objects while still satisfying real-time efficiency, with the Average Precision on 40 recall positions (AP40), respectively, increasing by 10.23% for partly occluded objects and 12.22% for mostly occluded objects in the KITTI benchmark. The codes are released at https://github.com/kagurua/Front-Side-Det [ABSTRACT FROM AUTHOR]

In the field of autonomous driving, existing semantic segmentation algorithms for road scenes have huge overhead and cannot meet the real-time performance of autonomous driving. Based on the overall structure of DeepLabV3+, this paper proposes a lightweight image semantic segmentation model with parallel feature processing, which takes into account both high accuracy and real-time performance. Firstly, MobileNetV2 is used as the backbone network to streamline the upsampling process and reduce the number of network parameters for network migration and training. Then, a dual-attention mechanism is introduced to combine with the null convolutional space pyramid module to form a parallel feature processing structure to improve segmentation accuracy. Finally, the parallel feature processing structure is then combined with MobileNetV2 to complete the extraction of image features. The experimental results show that the proposed model can guarantee efficient and accurate image segmentation with less system overhead and number of network parameters than the traditional model. The model achieves 73.61% mIoU in the Cityscapes dataset and processes a 512 x 512 image in 25 ms. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Logo detection has a wide range of applications in the multimedia field, such as video advertising research, brand awareness monitoring and analysis, trademark infringement detection, autonomous driving and intelligent transportation. Compared with other types of images, logo images in the real world have greater diversity in appearance and more complex backgrounds. Therefore, identifying logos from images is a challenge. A strong baseline method Trinity‐Yolo, is proposed, which incorporates attention mechanism, stripe pooling and weighted boxes fusion (WBF) into the state‐of‐the‐art Yolov4 framework for large‐scale logo detection. The attention mechanism improves the feature extraction ability of the deep detection model, the stripe pooling expands the field of view of the model and the weighted boxes fusion enables the model to obtain excellent corrections when outputting the prediction boxes. Trinity‐Yolo can solve the problems of lack of training data, multi‐scale objects and inconsistent bounding‐box regression. On the dataset LogoDet‐3K, the average performance of Trinity‐Yolo is 3% higher than that of Yolov4. Compared with other deep detection models, the performance of Trinity‐Yolo is improved more. The experimental performance on other existing datasets verifies the effectiveness of this method. [ABSTRACT FROM AUTHOR]

A lightweight network target detection algorithm was proposed, based on MobileNetv2_CA, focusing on the problem of high complexity, a large number of parameters, and the missed detection of small targets in the target detection network based on candidate regions and regression methods in autonomous driving scenarios. First, Mosaic image enhancement technology is used in the data pre-processing stage to enhance the feature extraction of small target scenes and complex scenes; second, the Coordinate Attention (CA) mechanism is embedded into the Mobilenetv2 backbone feature extraction network, combined with the PANet and Yolo detection heads for multi-scale feature fusion; finally, a Lightweight Object Detection Network is built. The experimental test results show that the designed network obtained the highest average detection accuracy of 81.43% on the Voc2007 + 2012 dataset, and obtained the highest average detection accuracy of 85.07% and a detection speed of 31.84 FPS on the KITTI dataset. The total amount of network parameters is only 39.5 M. This is beneficial to the engineering application of MobileNetv2 network in automatic driving. [ABSTRACT FROM AUTHOR]

Aimed at the vehicle/pedestrian visual sensing task under low-light conditions and the problems of small, dense objects and line-of-sight occlusion, a nighttime vehicle/pedestrian detection method was proposed. First, a vehicle/pedestrian detection algorithm was designed based on You Only Look Once X (YOLOX). The model structure was re-parameterized and lightened, and a coordinate-based attention mechanism was introduced into the backbone network to enhance the feature extraction efficiency of vehicle/pedestrian targets. A feature-scale fusion detection branch was added to the feature pyramid, while a loss function was designed, which combines Complete Intersection Over Union (CIoU) for target localization and Varifocal Loss for confidence prediction to improve the feature extraction ability for small, dense, and low-illumination targets. In addition, in order to further improve the detection accuracy of the algorithm under low-light conditions, a training strategy based on data domain transfer was proposed, which fuses the larger-scale daylight dataset with the smaller-scale nighttime dataset after low-illumination degrading. After low-light enhancement, training and testing were performed accordingly. The experimental results show that, compared with the original YOLOX model, the improved algorithm trained by the proposed data domain transfer strategy achieved better performance, and the mean Average Precision (mAP) increased by 5.9% to 82.4%. This research provided effective technical support for autonomous driving safety at night. [ABSTRACT FROM AUTHOR]

In this paper, we propose a 3D object detection method called MMAF-Net that is based on the multi-view and multi-stage adaptive fusion of RGB images and LiDAR point cloud data. This is an end-to-end architecture, which combines the characteristics of RGB images, the front view of point clouds based on reflection intensity, and the bird's eye view of point clouds. It also adopts a multi-stage fusion approach of "data-level fusion + feature-level fusion" to fully exploit the strength of multimodal information. Our proposed method addresses key challenges found in current 3D object detection methods for autonomous driving, including insufficient feature extraction from multimodal data, rudimentary fusion techniques, and sensitivity to distance and occlusion. To ensure the comprehensive integration of multimodal information, we present a series of targeted fusion methods. Firstly, we propose a novel input form that encodes dense point cloud reflectivity information into the image to enhance its representational power. Secondly, we design the Region Attention Adaptive Fusion module utilizing an attention mechanism to guide the network in adaptively adjusting the importance of different features. Finally, we extend the 2D DIOU (Distance Intersection over Union) loss function to 3D and develop a joint regression loss based on 3D_DIOU and SmoothL1 to optimize the similarity between detected and ground truth boxes. The experimental results on the KITTI dataset demonstrate that MMAF-Net effectively addresses the challenges posed by highly obscured or crowded scenes while maintaining real-time performance and improving the detection accuracy of smaller and more difficult objects that are occluded at far distances. • A novel object detection method is proposed integrating RGB images and LiDAR data. • This study tests the method on the KITTI dataset. • This method tackles highly obscured or crowded scenes for autonomous driving. • This method improves the detection accuracy of smaller and occluded targets far away. [ABSTRACT FROM AUTHOR]

At present, pedestrian detection is widely applied to autonomous driving and intelligent transportation and robots, etc. But the balance between accuracy and speed is still not reached. In complex background with high pedestrian density and serious occlusion, missing detection or false detection may occur by pedestrian detection models based on center and scale prediction (CSP). An improved pedestrian detection method based on channel feature fusion and enhanced semantic segmentation is presented. A feature fusion module based on squeeze and excitation is proposed in feature extraction. Multi-scale feature maps are fused to obtain faster detection speed and higher detection accuracy. An enhanced semantic segmentation module is presented in detection head to solve missing detection for long-distance pedestrians. CIOU (Complete Intersection Over Union) loss function is used to improve the confidence levels of pedestrians. Experiments on different networks, scales of feature fusion and detection methods are carried out to verify the performance of proposed approach. The experimental results show that the proposed model can detect pedestrians with high accuracy in occluded, dense and long-distance scenes. The detection speed can be accelerated while keeping low missed detection rate and less computational cost. It is shown that the approach can achieve high accuracy and robustness especially in complex background. [ABSTRACT FROM AUTHOR]

Three-dimensional object detection is the core of an autonomous driving perception system, which detects and analyzes targets around the vehicle to obtain their sizes, shapes, and categories to provide reliable operational decisions for achieving autonomous driving. To improve the detection and localization accuracy of multi-object targets such as surrounding vehicles and pedestrians in autonomous driving scenarios, based on PointPillars fast object detection network, a three-dimensional object detection algorithm based on the channel attention mechanism, ECA Modules-PointPillars, is proposed. Firstly, the improved algorithm uses point cloud columnarization features to convert a three-dimensional point cloud into a two-dimensional pseudo-image. Then, combining the 2D backbone network for feature extraction with the Efficient Channel Attention (ECA) modules to achieve the enhancement of the positional feature information in the pseudo-image and the weakening of the irrelevant feature information such as background noise. Finally, the single-shot multibox detector (SSD) algorithm was used to complete the 3D object detection task. The experimental results show that the improved algorithm improves the mAP by 3.84% and 4.04% in BEV mode and 3D mode, respectively, compared to PointPillars, which improves the mAP by 4.64% and 5.89% in BEV mode and 3D mode, respectively, compared to F-PointNet, improves the mAP by 11.78% and 14.19% in BEV mode and 3D mode, respectively, compared to VoxelNet, and improves the mAP by 9.47% and 6.55% in BEV mode and 3D mode, respectively, compared to SECOND, demonstrating the effectiveness and reliability of the improved algorithms in autonomous driving scenarios. [ABSTRACT FROM AUTHOR]

Accurate and real-time monitoring of the shoreline through cameras is an invaluable guarantee for the safety of near-shore navigation and berthing of unmanned surface vehicles; existing shoreline detection methods cannot meet both these requirements. Therefore, we propose an improved shoreline detection method to detect shorelines accurately and in real time. We define shoreline detection as the combination of water surface area segmentation and edge detection, the key to which is segmentation. To detect shorelines accurately and in real time, we propose an improved U-Net for water segmentation. This network is based on U-Net, using ResNet-34 as the backbone to enhance the feature extraction capability, with a concise decoder integrated attention mechanism to improve the processing speed while ensuring the accuracy of water surface segmentation. We also introduce transfer learning to improve training efficiency and solve the problem of insufficient data. When obtaining the segmentation result, the Laplace edge detection algorithm is applied to detect the shoreline. Experiments show that our network achieves 97.05% MIoU and 40 FPS with the fewest parameters, which is better than mainstream segmentation networks, and also demonstrate that our shoreline detection method can effectively detect shorelines in real time in various environments. [ABSTRACT FROM AUTHOR]

For autonomous driving systems, vehicle detection is an important part and challenging problem due to the complex traffic scenes and poor computing resources. This paper proposes an improved SSD(single shot mutlibox detector) algorithm for the fast detection of vehicles in traffic scenes. MobileNet v2 is selected as the backbone feature extraction network for SSD, which improves the real-time performance of the algorithm. To improve detection accuracy, the channel attention mechanism is utilized for feature weighting, and the deconvolution module is utilized to construct a bottom–top feature fusion structure. The experimental results show that the average precision of the proposed algorithm on the BDD100K and KITTI datasets is 82.59% and 84.83%, respectively. The single inference time of the algorithm is 73ms, which is only about 5/11 of the original model, realizing the improvement of inference speed and prediction accuracy. • Vision-based surrounding vehicle detection is utilized for intelligent driving environment sensing to ensure driving safety. • The proposed method has three improvements to the single shot mutlibox detector (SSD), including a lightweight backbone network, the attention mechanism, and the deconvolution module. • The proposed method simplifies hardware requirements, reduces computational costs, and meets the needs of practical application. • The proposed method could automatically detect vehicles in various complex traffic scenes. [ABSTRACT FROM AUTHOR]

Object detection is becoming increasingly significant for autonomous-driving system. However, poor accuracy or low inference performance limits current object detectors in applying to autonomous driving. In this work, a fast and accurate object detector termed as SA-YOLOv3, is proposed by introducing dilated convolution and self-attention module (SAM) into the architecture of YOLOv3. Furthermore, loss function based on GIoU and focal loss is reconstructed to further optimize detection performance. With an input size of $512\times 512$ , our proposed SA-YOLOv3 improves YOLOv3 by 2.58 mAP and 2.63 mAP on KITTI and BDD100K benchmarks, with real-time inference (more than 40 FPS). When compared with other state-of-the-art detectors, it reports better trade-off in terms of detection accuracy and speed, indicating the suitability for autonomous-driving application. To our best knowledge, it is the first method that incorporates YOLOv3 with attention mechanism, and we expect this work would guide for autonomous-driving research in the future. [ABSTRACT FROM AUTHOR]

In recent years, self-supervised monocular depth estimation has gained popularity among researchers because it uses only a single camera at a much lower cost than the direct use of laser sensors to acquire depth. Although monocular self-supervised methods can obtain dense depths, the estimation accuracy needs to be further improved for better applications in scenarios such as autonomous driving and robot perception. In this paper, we innovatively combine soft attention and hard attention with two new ideas to improve self-supervised monocular depth estimation: (1) a soft attention module and (2) a hard attention strategy. We integrate the soft attention module in the model architecture to enhance feature extraction in both spatial and channel dimensions, adding only a small number of parameters. Unlike traditional fusion approaches, we use the hard attention strategy to enhance the fusion of generated multi-scale depth predictions. Further experiments demonstrate that our method can achieve the best self-supervised performance both on the standard KITTI benchmark and the Make3D dataset. [ABSTRACT FROM AUTHOR]