Low-cost implementation of bird's-eye view system for camera-on-vehicle

Luo, Lei; Koh, In-Sung; Min, Kyeong-Yuk; Wang, Jun; Chong, Jong‐Wha

doi:10.1109/icce.2010.5418845

Cited by 11 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, DSP units' utilisation is higher for [6] due to additional circuitry required to implement sub-sampled LUT. This is true for all techniques proposed in the literature to reduce the size of LUT through various compression techniques [22][23][24][25]. The overhead of the arithmetic circuit required to decompress LUT values at the run-time does not justify the use of LUT to save overall logic resources.…”

Section: Fpga Synthesis Resultsmentioning

confidence: 99%

“…Several researchers have realised that the LUT contents have a very low entropy value and hence can be efficiently compressed using differential, Huffman or run-length encoding [22][23][24] to save memory resources at the expense of an additional run-time decoding hardware. BEV hardware described by Luo et al [25] uses a differentially encoded LUT. Similarly, the BEV block in Simulink Vision HDL toolbox uses a run-length encoded LUT in its automatically generated HDL code.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Resource‐efficient FPGA implementation of perspective transformation for bird's eye view generation using high‐level synthesis framework

Bilal

2019

IET Circuits, Devices & Systems

View full text Add to dashboard Cite

Bird's eye view (BEV) generation from front-looking video stream is considered an important pre-processing task in various computer vision applications such as driver assistance systems. In this work, hardware implementation of this process using high-level synthesis in Simulink environment has been considered for rapid prototyping under real-time constraints. Traditionally, researchers have employed lookup table-based approaches to circumvent the exorbitant cost of implementing arithmetic modules associated with the perspective transformation. The hardware implementation scheme proposed here, however, demonstrates that a polynomial approximation over the limited domain of the involved operands not only saves precious hardware resources but also provides better fixed-point precision. Synthesis results on Zynq-7000 FPGA show that the proposed circuit reduces the block memory utilisation by 9% compared to the lookup table-based built-in Simulink Vision HDL block. The proposed design evaluates the results in fixed-point format which is essential for subsequent bilinear interpolation to produce high-fidelity output frame, albeit at the cost of 4% increase in DSP48E utilisation. The approximation error of the proposed solution is less than quarter-pixel on average. The proposed hardware has been integrated as an IP core in a hardware-software co-design system. The whole framework is publicly available to facilitate practitioners and researchers.

show abstract

Section: Fpga Synthesis Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Resource‐efficient FPGA implementation of perspective transformation for bird's eye view generation using high‐level synthesis framework

Bilal

2019

IET Circuits, Devices & Systems

View full text Add to dashboard Cite

show abstract

Section: Setting Of a Region Of Interest (Roi) For Iptmentioning

confidence: 99%

“…This paper focuses on applying the IPT technique to the tunnel CCTV image, referred to as the original image (OI), and this involves the initial establishment of a region of interest (ROI) [29]. The ROI is defined as a quadrangular shape, conforming to the road width and CCTV installation spacing when the image is stretched and observed on a horizontal plane, as illustrated in Figure 2a [29]. In this context, Figure 2b serves as an OI coordinate system, its origin is at the top left corner, the rightward horizontal direction is denoted as the x axis, and the downward vertical direction is denoted as the y axis.…”

Section: Setting Of a Region Of Interest (Roi) For Iptmentioning

confidence: 99%

Deep Learning-Based Consistent Object Detection in Distance on Highly Perspective Region

Lee,

Gong,

Ryu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

CCTVs are commonly used for traffic monitoring and accident detection, but their images suffer from severe perspective distortion causing object size reduction with distance. This issue is exacerbated in tunnel CCTVs, positioned low due to space constraints, leading to challenging object detection, especially for distant small objects, due to perspective effects. To address this, this study proposes a solution involving a region of interest setup and an inverse perspective transformation technique. The transformed images, achieved through this technique, enlarge distant objects, maintaining object detection performance and appearance velocity across distances. To validate this, artificial CCTV images were generated in a virtual tunnel environment, creating original and transformed image datasets under identical conditions. Comparisons were made between the appearance velocity and object size of individual vehicles and for deep learning model performance with multiple moving vehicles. The evaluation was conducted across four distance intervals (50 m to 200 m) from the tunnel CCTV location. The results reveal that the model using original images experiences a significant decline in object detection performance beyond 100 m, while the transformed image-based model maintains a consistent performance up to the distance of 200 m.

show abstract