PSANet: Pyramid Splitting and Aggregation Network for 3D Object Detection in Point Cloud

Li, Fangyu; Jin, Weizheng; Fan, Cien; Zou, Lian; Chen, Qingsheng; Li, Xiaopeng; Jiang, Hao; Liu, Yifeng

doi:10.3390/s21010136

Cited by 16 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CSP network structure reduces the amount of model calculation while maintaining accuracy. The activation function in CSPDarknet53 is the Mish activation function, as given by Equation (7).…”

Section: Traffic Cone Detection With Colour Imagesmentioning

confidence: 99%

“…Long-range detection sensors, like LiDAR etc., can accurately measure 3D positions throughout the whole day, but object detection based on LiDAR point clouds is challenging. Due to the sparse reflection detection, point clouds lose the colour and whole outline features of objects, and they cannot sufficiently detect small targets at long distances [7]. However, as a cost-effective solution, machine vision technology can solve these issues because images provide rich colour and texture information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real‐time traffic cone detection for autonomous driving based on YOLOv4

Wang

Xie

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

A temporary road composed of traffic cones is an indispensable practical scene for the realization of automatic driving technology. However, the detection of traffic cones is a challenging issue because of their small volume and unfixed position. This work proposes a novel method that fuses colour and depth image information for traffic cone detection. Traffic cones are captured by a special machine vision system consisting of two monochrome cameras for cone distance perception and two colour cameras for cone colour acquisition. Via the YOLOv4 algorithm based on the Darknet platform and a detection result matching algorithm, the position of the traffic cone can be obtained and path planning can be performed. The results of experiments show that the proposed method can recognize red, blue, and yellow traffic cones in colour images with an average detection time of 35.46 ms and respective accuracies of 97.51%, 98.63%, and 97.29%. Compared with the previous traffic cone detection research, the proposed algorithm was found to exhibit advantages in small target sensitivity and overall detection accuracy in both static and dynamic experiments.

show abstract

Section: Traffic Cone Detection With Colour Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real‐time traffic cone detection for autonomous driving based on YOLOv4

Wang

Xie

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Since LiDAR sensors function well even in adverse lighting conditions, they are crucial to many applications. In these applications, 3D object detection is an important task [ 22 , 23 , 24 , 25 , 26 ]. However, for those objects without spatial volumes, such as road signs on the ground, they cannot be detected using the point cloud data.…”

Section: Related Workmentioning

confidence: 99%

LiDAR Intensity Completion: Fully Exploiting the Message from LiDAR Sensors

Dai

Chen

Huang

et al. 2022

Sensors

View full text Add to dashboard Cite

Light Detection and Ranging (LiDAR) systems are novel sensors that provide robust distance and reflection strength by active pulsed laser beams. They have significant advantages over visual cameras by providing active depth and intensity measurements that are robust to ambient illumination. However, the systemsstill pay limited attention to intensity measurements since the output intensity maps of LiDAR sensors are different from conventional cameras and are too sparse. In this work, we propose exploiting the information from both intensity and depth measurements simultaneously to complete the LiDAR intensity maps. With the completed intensity maps, mature computer vision techniques can work well on the LiDAR data without any specific adjustment. We propose an end-to-end convolutional neural network named LiDAR-Net to jointly complete the sparse intensity and depth measurements by exploiting their correlations. For network training, an intensity fusion method is proposed to generate the ground truth. Experiment results indicate that intensity–depth fusion can benefit the task and improve performance. We further apply an off-the-shelf object (lane) segmentation algorithm to the completed intensity maps, which delivers consistent robust to ambient illumination performance. We believe that the intensity completion method allows LiDAR sensors to cope with a broader range of practice applications.

show abstract

“…Since then, there have been some improved methods for small-target detection in the field of deep learning, such as multiscale fusion, scale invariance, and so on. Feature Pyramid Networks (FPNs) [16,17] use low-level location information with high-level semantic information by propagating the high-level features down. e problem of small-target detection results in part from deep learning target detection algorithms only using top-level feature mapping for classification and prediction and ignoring the location information of low-level features.…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Data Detection Based on Multiscale Fusion and Attention Mechanism

Huang

Cheng

Luca

2021

Mobile Information Systems

View full text Add to dashboard Cite

Remote sensing images are often of low quality due to the limitations of the equipment, resulting in poor image accuracy, and it is extremely difficult to identify the target object when it is blurred or small. The main challenge is that objects in sensing images have very few pixels. Traditional convolutional networks are complicated to extract enough information through local convolution and are easily disturbed by noise points, so they are usually not ideal for classifying and diagnosing small targets. The current solution is to process the feature map information at multiple scales, but this method does not consider the supplementary effect of the context information of the feature map on the semantics. In this work, in order to enable CNNs to make full use of context information and improve its representation ability, we propose a residual attention function fusion method, which improves the representation ability of feature maps by fusing contextual feature map information of different scales, and then propose a spatial attention mechanism for global pixel point convolution response. This method compresses global pixels through convolution, weights the original feature map pixels, reduces noise interference, and improves the network’s ability to grasp global critical pixel information. In experiments, the remote sensing ship image recognition experiments on remote sensing image data sets show that the network structure can improve the performance of small-target detection. The results on cifar10 and cifar100 prove that the attention mechanism is universal and practical.

show abstract

PSANet: Pyramid Splitting and Aggregation Network for 3D Object Detection in Point Cloud

Cited by 16 publications

References 32 publications

Real‐time traffic cone detection for autonomous driving based on YOLOv4

Real‐time traffic cone detection for autonomous driving based on YOLOv4

LiDAR Intensity Completion: Fully Exploiting the Message from LiDAR Sensors

Remote Sensing Data Detection Based on Multiscale Fusion and Attention Mechanism

Contact Info

Product

Resources

About