Search

Object detection is one of the core technologies for autonomous driving. Current road object detection mainly relies on visible light, which is prone to missed detections and false alarms in rainy, night-time, and foggy scenes. Multispectral object detection based on the fusion of RGB and infrared images can effectively address the challenges of complex and changing road scenes, improving the detection performance of current algorithms in complex scenarios. However, previous multispectral detection algorithms suffer from issues such as poor fusion of dual-mode information, poor detection performance for multi-scale objects, and inadequate utilization of semantic information. To address these challenges and enhance the detection performance in complex road scenes, this paper proposes a novel multispectral object detection algorithm called MRD-YOLO. In MRD-YOLO, we utilize interaction-based feature extraction to effectively fuse information and introduce the BIC-Fusion module with attention guidance to fuse different modal information. We also incorporate the SAConv module to improve the model's detection performance for multi-scale objects and utilize the AIFI structure to enhance the utilization of semantic information. Finally, we conduct experiments on two major public datasets, FLIR_Aligned and M3FD. The experimental results demonstrate that compared to other algorithms, the proposed algorithm achieves superior detection performance in complex road scenes. [ABSTRACT FROM AUTHOR]

The traditional rearview mirror method cannot fully guarantee safety when driving trucks. RGB and infrared images collected by cameras are used for registration and recognition, so as to achieve the perception of surroundings and ensure safe driving. The traditional scale-invariant feature transform (SIFT) algorithm has a mismatching rate, and the YOLO algorithm has an optimization space in feature extraction. To address these issues, this paper proposes a truck surround sensing technique based on multi-features and an improved YOLOv5 algorithm. Firstly, the edge corner points and infrared features of the preset target region are extracted, and then a feature point set containing the improved SIFT algorithm is generated for registration. Finally, the YOLOv5 algorithm is improved by fusing infrared features and introducing a composite prediction mechanism at the prediction end. The simulation results show that, on average, the image stitching accuracy is improved by 17%, the time is reduced by 89%, and the target recognition accuracy is improved by 2.86%. The experimental results show that this method can effectively perceive the surroundings of trucks, accurately identify targets, and reduce the missed alarm rate and false alarm rate. [ABSTRACT FROM AUTHOR]

Multi-robot Simultaneous Localization and Mapping (SLAM) systems employing 2D lidar scans are effective for exploration and navigation within GNSS-limited environments. However, scalability concerns arise with larger environments and increased robot numbers, as 2D mapping necessitates substantial processor memory and inter-robot communication bandwidth. Thus, data compression prior to transmission becomes imperative. This study investigates the problem of communication-efficient multi-robot SLAM based on 2D maps and introduces an architecture that enables compressed communication, facilitating the transmission of full maps with significantly reduced bandwidth. We propose a framework employing a lightweight feature extraction Convolutional Neural Network (CNN) for a full map, followed by an encoder combining Huffman and Run-Length Encoding (RLE) algorithms to further compress a full map. Subsequently, a lightweight recovery CNN was designed to restore map features. Experimental validation involves applying our compressed communication framework to a two-robot SLAM system. The results demonstrate that our approach reduces communication overhead by 99% while maintaining map quality. This compressed communication strategy effectively addresses bandwidth constraints in multi-robot SLAM scenarios, offering a practical solution for collaborative SLAM applications. [ABSTRACT FROM AUTHOR]

Cooperative perception in the field of connected autonomous vehicles (CAVs) aims to overcome the inherent limitations of single-vehicle perception systems, including long-range occlusion, low resolution, and susceptibility to weather interference. In this regard, we propose a high-precision 3D object detection V2V cooperative perception algorithm. The algorithm utilizes a voxel grid-based statistical filter to effectively denoise point cloud data to obtain clean and reliable data. In addition, we design a feature extraction network based on the fusion of voxels and PointPillars and encode it to generate BEV features, which solves the spatial feature interaction problem lacking in the PointPillars approach and enhances the semantic information of the extracted features. A maximum pooling technique is used to reduce the dimensionality and generate pseudoimages, thereby skipping complex 3D convolutional computation. To facilitate effective feature fusion, we design a feature level-based crossvehicle feature fusion module. Experimental validation is conducted using the OPV2V dataset to assess vehicle coperception performance and compare it with existing mainstream coperception algorithms. Ablation experiments are also carried out to confirm the contributions of this approach. Experimental results show that our architecture achieves lightweighting with a higher average precision (AP) than other existing models. [ABSTRACT FROM AUTHOR]

Current challenges in visible and infrared image fusion include color information distortion, texture detail loss, and target edge blur. To address these issues, a fusion algorithm based on double-domain transform filter and nonlinear contrast transform feature extraction (DDCTFuse) is proposed. First, for the problem of incomplete detail extraction that exists in the traditional transform domain image decomposition, an adaptive high-pass filter is proposed to decompose images into high-frequency and low-frequency portions. Second, in order to address the issue of fuzzy fusion target caused by contrast loss during the fusion process, a novel feature extraction algorithm is devised based on a novel nonlinear transform function. Finally, the fusion results are optimized and color-corrected by our proposed spatial-domain logical filter, in order to solve the color loss and edge blur generated in the fusion process. To validate the benefits of the proposed algorithm, nine classical algorithms are compared on the LLVIP, MSRS, INO, and Roadscene datasets. The results of these experiments indicate that the proposed fusion algorithm exhibits distinct targets, provides comprehensive scene information, and offers significant image contrast. [ABSTRACT FROM AUTHOR]

Aiming at the problems of incomplete dehazing, color distortion, and loss of detail and edge information encountered by existing algorithms when processing images of underground coal mines, an image dehazing algorithm for underground coal mines, named CAB CA DSConv Fusion gUNet (CCDF-gUNet), is proposed. First, Dynamic Snake Convolution (DSConv) is introduced to replace traditional convolutions, enhancing the feature extraction capability. Second, residual attention convolution blocks are constructed to simultaneously focus on both local and global information in images. Additionally, the Coordinate Attention (CA) module is utilized to learn the coordinate information of features so that the model can better capture the key information in images. Furthermore, to simultaneously focus on the detail and structural consistency of images, a fusion loss function is introduced. Finally, based on the test verification of the public dataset Haze-4K, the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Mean Squared Error (MSE) are 30.72 dB, 0.976, and 55.04, respectively, and on a self-made underground coal mine dataset, they are 31.18 dB, 0.971, and 49.66, respectively. The experimental results show that the algorithm performs well in dehazing, effectively avoids color distortion, and retains image details and edge information, providing some theoretical references for image processing in coal mine surveillance videos. [ABSTRACT FROM AUTHOR]

To tackle the challenges of weak sensing capacity for multi-scale objects, high missed detection rates for occluded targets, and difficulties for model deployment in detection tasks of intelligent roadside perception systems, the PDT-YOLO algorithm based on YOLOv7-tiny is proposed. Firstly, we introduce the intra-scale feature interaction module (AIFI) and reconstruct the feature pyramid structure to enhance the detection accuracy of multi-scale targets. Secondly, a lightweight convolution module (GSConv) is introduced to construct a multi-scale efficient layer aggregation network module (ETG), enhancing the network feature extraction ability while maintaining weight. Thirdly, multi-attention mechanisms are integrated to optimize the feature expression ability of occluded targets in complex scenarios, Finally, Wise-IoU with a dynamic non-monotonic focusing mechanism improves the accuracy and generalization ability of model sensing. Compared with YOLOv7-tiny, PDT-YOLO on the DAIR-V2X-C dataset improves mAP50 and mAP50:95 by 4.6% and 12.8%, with a parameter count of 6.1 million; on the IVODC dataset by 15.7% and 11.1%. We deployed the PDT-YOLO in an actual traffic environment based on a robot operating system (ROS), with a detection frame rate of 90 FPS, which can meet the needs of roadside object detection and edge deployment in complex traffic scenes. [ABSTRACT FROM AUTHOR]

It is important to achieve the 3D reconstruction of UAV remote sensing images in deep learning-based multi-view stereo (MVS) vision. The lack of obvious texture features and detailed edges in UAV remote sensing images leads to inaccurate feature point matching or depth estimation. To address this problem, this study improves the TransMVSNet algorithm in the field of 3D reconstruction by optimizing its feature extraction network and costumed body depth prediction network. The improvement is mainly achieved by extracting features with the Asymptotic Pyramidal Network (AFPN) and assigning weights to different levels of features through the ASFF module to increase the importance of key levels and also using the UNet structured network combined with an attention mechanism to predict the depth information, which also extracts the key area information. It aims to improve the performance and accuracy of the TransMVSNet algorithm's 3D reconstruction of UAV remote sensing images. In this work, we have performed comparative experiments and quantitative evaluation with other algorithms on the DTU dataset as well as on a large UAV remote sensing image dataset. After a large number of experimental studies, it is shown that our improved TransMVSNet algorithm has better performance and robustness, providing a valuable reference for research and application in the field of 3D reconstruction of UAV remote sensing images. [ABSTRACT FROM AUTHOR]