SSA3D: Semantic Segmentation Assisted One-Stage Three-Dimensional Vehicle Object Detection

Huang, Shangfeng; Cai, Guorong; Wang, Zongyue; Xia, Qiming; Wang, Ruisheng

doi:10.1109/tits.2021.3133476

Cited by 15 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the Euclidean distance-based measure, the F1 score is also used to evaluate the BFQ detection performance. The F1 score takes into account the normalized error to determine whether a prediction is correct and combines precision and recall using Equation (10), where precision and recall are computed by Equations ( 11) and ( 12), respectively. To be considered a correctly detected BFQ, the average position error must be less than the threshold.…”

Section: Evaluation Criteriamentioning

confidence: 99%

“…For instance, autonomous driving based on vehicle-to-infrastructure (V2I) prevents accidents or control vehicles using accurate positions provided by infrastructure surveillance cameras. Various sensors have been used for vehicle detection, including monocular cameras [ 6 , 7 , 8 , 9 ], lidars [ 10 , 11 ], lidar–camera fusion [ 12 , 13 ], and stereo cameras [ 14 ]. Among them, monocular cameras are preferable because they can be installed at a low cost and require less computational load.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CNN-Based Vehicle Bottom Face Quadrilateral Detection Using Surveillance Cameras for Intelligent Transportation Systems

Kim

Jung

Suhr

2023

Sensors

View full text Add to dashboard Cite

In intelligent transportation systems, it is essential to estimate the vehicle position accurately. To this end, it is preferred to detect vehicles as a bottom face quadrilateral (BFQ) rather than an axis-aligned bounding box. Although there have been some methods for detecting the vehicle BFQ using vehicle-mounted cameras, few studies have been conducted using surveillance cameras. Therefore, this paper conducts a comparative study on various approaches for detecting the vehicle BFQ in surveillance camera environments. Three approaches were selected for comparison, including corner-based, position/size/angle-based, and line-based. For comparison, this paper suggests a way to implement the vehicle BFQ detectors by simply adding extra heads to one of the most widely used real-time object detectors, YOLO. In experiments, it was shown that the vehicle BFQ can be adequately detected by using the suggested implementation, and the three approaches were quantitatively evaluated, compared, and analyzed.

show abstract

Section: Evaluation Criteriamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CNN-Based Vehicle Bottom Face Quadrilateral Detection Using Surveillance Cameras for Intelligent Transportation Systems

Kim

Jung

Suhr

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…HDNet [44] estimates ground height and road information through HDMap to achieve better detection results. Inspired by PointNet++ [21], PointCNN [45], and PointConv [46], which use feature propagation layers (FP layers) to recover the sampled points to the original input size and extract features more effectively, SSA3D [47] regards FP layers as an auxiliary task to aid 3D object detection. While these methods perform full-resolution semantic segmentation, we only employ local segmentation on the candidate points.…”

Section: Auxiliary Task For Point Cloud Detectorsmentioning

confidence: 99%

Segmentation Can Aid Detection: Segmentation-Guided Single Stage Detection for 3D Point Cloud

et al. 2023

View full text Add to dashboard Cite

Detecting accurate 3D bounding boxes from point cloud data plays an essential role in autonomous driving. However, improving performance requires more complex models, which come with high memory and computational cost. In this work, we design a Segmentation-Guided Auxiliary Network (SGAN) to improve the localization quality of detection. The points from different levels are concatenated to generate the multi-scale feature for the points used for prediction, i.e., candidate points. SGAN is jointly optimized by two tasks of candidate points—segmentation and center estimation—and it is only used in training and therefore introduces no extra computation in the inference stage. Furthermore, we consider that point-based detectors suffer from the outline points of sampling, so we explore the correlation between the data and propose the Point Cloud External Attention (PCEA) to extract the semantic features with a low memory cost. Our method SGSSD achieves a large margin against the baseline on the KITTI and Waymo datasets, and it runs at 25 FPS for inference on the KITTI test set with a single NVIDIA RTX 3090.

show abstract

CG-SSD: Corner guided single stage 3D object detection from LiDAR point cloud

Chen

Wang

et al. 2022

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

SSA3D: Semantic Segmentation Assisted One-Stage Three-Dimensional Vehicle Object Detection

Cited by 15 publications

References 42 publications

CNN-Based Vehicle Bottom Face Quadrilateral Detection Using Surveillance Cameras for Intelligent Transportation Systems

CNN-Based Vehicle Bottom Face Quadrilateral Detection Using Surveillance Cameras for Intelligent Transportation Systems

Segmentation Can Aid Detection: Segmentation-Guided Single Stage Detection for 3D Point Cloud

CG-SSD: Corner guided single stage 3D object detection from LiDAR point cloud

Contact Info

Product

Resources

About