Beyond Bounding Boxes: Using Bounding Shapes for Real-Time 3D Vehicle Detection from Monocular RGB Images

Gählert, Nils; Wan, Jun-Jun; Weber, Michael; Zöllner, J. Marius; Franke, Uwe; Denzler, Joachim

doi:10.1109/ivs.2019.8814036

Cited by 7 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 9 ], the corners were located by transforming the ROI from the 2D bounding box to column vectors and passed it through the Softmax layer. In [ 7 , 13 , 26 ], only four out of eight corners were detected. In addition to four corners of the BFQ, [ 13 , 26 ] found two heights and one height information from the ground to the bottom and top face, respectively.…”

Section: Related Workmentioning

confidence: 99%

“…In addition to four corners of the BFQ, [ 13 , 26 ] found two heights and one height information from the ground to the bottom and top face, respectively. In [ 7 ], the Single Shot MultiBox Detector [ 45 ] was extended to output 3D bounding shapes using predefined four corners instead of 2D bounding boxes. Three of the four corners form the BFQ, and the remaining corner is used to determine the height.…”

Section: Related Workmentioning

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%

“…Based on the way to represent the quadrilateral, these methods can be categorized into three approaches: corner-based, position/size/angle (PSA)-based, and line-based. The corner-based approach represents the BFQ with its four corners [ 6 , 7 , 8 , 9 , 13 , 20 , 21 , 22 , 23 , 24 , 25 , 26 ]. The PSA-based approach represents the BFQ with its position, size, and angle [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

“…While the so-called two-stage detectors like Region-CNN [13] and its descendants only played a minor role in autonomous driving due to their long and unpredictable runtime, one-stage detectors like the YOLO family ( [14], [8], [15], [16]), SSD [6], RetinaNet [4] and already OverFeat [17] made their way into autonomous driving functions like [18]. Recently also approaches for 3D object detection in the autonomous driving domain emerged [19], [20].…”

Section: A Object Detectionmentioning

confidence: 99%

Temporal Feature Networks for CNN based Object Detection

Weber¹,

Wald²,

Zöllner³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

For reliable environment perception, the use of temporal information is essential in some situations. Especially for object detection, sometimes a situation can only be understood in the right perspective through temporal information. Since image-based object detectors are currently based almost exclusively on CNN architectures, an extension of their feature extraction with temporal features seems promising.Within this work we investigate different architectural components for a CNN-based temporal information extraction. We present a Temporal Feature Network which is based on the insights gained from our architectural investigations. This network is trained from scratch without any ImageNet information based pre-training as these images are not available with temporal information. The object detector based on this network is evaluated against the non-temporal counterpart as baseline and achieves competitive results in an evaluation on the KITTI object detection dataset.

show abstract

Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometrically Constrained Keypoints in Real-Time

Gählert

Wan

Jourdan

et al. 2020

2020 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Beyond Bounding Boxes: Using Bounding Shapes for Real-Time 3D Vehicle Detection from Monocular RGB Images

Cited by 7 publications

References 32 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

Temporal Feature Networks for CNN based Object Detection

Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometrically Constrained Keypoints in Real-Time

Contact Info

Product

Resources

About