Supporting Detection of Near and Far Pedestrians in a Collision Prediction System

Cambuim, Lucas F. S.; Barros, Edna

doi:10.5220/0010253706690676

Cited by 2 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section describes the techniques and algorithms of the pedestrian detection (PD) system. It is essential to make it clear that this section is not the contribution of this work but of our previous work [6]. It serves to support the description of our proposed hardware architecture in Section 3.…”

Section: Pedestrian Detection (Pd) Systemmentioning

confidence: 99%

“…(1) coverage in large ranges of distances and (2) fast response. PD systems with such characteristics permit PCP systems to predict a collision earlier [6].…”

Section: Introductionmentioning

confidence: 99%

“…While the pyramid aims to encounter pedestrians larger than the detection window dimension, the windows of various sizes permit locating pedestrians that appear with smaller dimensions. Our previous work [6] demonstrated that the combination of detectors and the image pyramid enabled finding pedestrians further and further away. However, the processing rate of the GPU-based solution proved to be non-scalable in terms of image resolution.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, this work proposes an FPGA-based processing architecture of our detector [6] to further enhance the PCP system processing performance. The proposed detector is similar to the works [13,19,22], but does not approximate the cell calculation nor adopt a double frequency strategy.…”

Section: Introductionmentioning

confidence: 99%

“…The processing rate of the entire PCP system for processing HD images is approximately 66.2 FPS. This rate allowed an increase of 3.3 m in decision-making distance for a vehicle traveling at 60km/h compared to our previous PCP system [6] which processes the collision prediction at 30 FPS.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

FPGA-Based Pedestrian Detection for Collision Prediction System

Cambuim

Barros

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Pedestrian detection (PD) systems capable of locating pedestrians over large distances and locating them faster are needed in Pedestrian Collision Prediction (PCP) systems to increase the decision-making distance. This paper proposes a performance-optimized FPGA implementation of a HOG-SVM-based PD system with support for image pyramids and detection windows of different sizes to locate near and far pedestrians. This work proposes a hardware architecture that can process one pixel per clock cycle by exploring data and temporal parallelism using techniques such as pipeline and spatial division of data between parallel processing units. The proposed architecture for the PD module was validated in FPGA and integrated with the stereo semi-global matching (SGM) module, also prototyped in FPGA. Processing two windows of different dimensions permitted a reduction in miss rate of at least 6% compared to a uniquely sized window detector. The performances achieved by the PD system and the PCP system in HD resolution were 100 and 66.2 frames per second (FPS), respectively. The performance improvement achieved by the PCP system with the addition of our PD module permitted an increase in decision-making distance of 3.3 m compared to a PCP system that processes at 30 FPS.

show abstract

Section: Pedestrian Detection (Pd) Systemmentioning

confidence: 99%

“…(1) coverage in large ranges of distances and (2) fast response. PD systems with such characteristics permit PCP systems to predict a collision earlier [6].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%