ROS-Based Pedestrian Detection and Distance Estimation Algorithm Using Stereo Vision, Leddar and CNN

Mukherjee, Anjali; Adarsh, S.; Ramachandran, K. I.

doi:10.1007/978-981-15-5400-1_13

Cited by 6 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…En (Mukherjee et al, 2020), presentan un sistema basado en la plataforma ROS, para la detección y estimación de distancia de peatones. Para la detección, utilizan una cámara de visión estéreo ZED y la arquitetura de red convolucional YO-LOv2.…”

Section: Antecedentesunclassified

Reconocimiento y estimación de posición relativa de objetos en entornos controlados

Luna-Taylor

Rosas

Torres

et al. 2022

ICBI

View full text Add to dashboard Cite

En este proyecto, se presenta un sistema de reconocimiento y clasificación de objetos que se encuentran en su entorno, para un robot de asistencia, así como la estimación de la posición relativa de estos con respecto al robot. Para el reconocimiento y clasificación de los objetos, se aplicaron técnicas de visión artificial basadas en herramientas de segmentación semántica, como son redes neuronales convolucionales. Para la estimación de la posición relativa de los objetos, una vez identificados, se implementó una técnica de visión estereoscópica. Los resultados de los experimentos muestran un 90.6% de precisión en el reconocimiento y clasificación, y un error medio de 5 cm al estimar la posición relativa de los objetos.

show abstract

Section: Antecedentesunclassified

Reconocimiento y estimación de posición relativa de objetos en entornos controlados

Luna-Taylor

Rosas

Torres

et al. 2022

ICBI

View full text Add to dashboard Cite

show abstract

“…CNN-based object detection models, a branch of AI, are divided into the 1-stage detector that performs detection and classification at once and the 2-stage detector that separates detection and classification, and various models such as simple CNN [29][30][31][32][33][34][35] and R-CNN [32,[36][37][38][39][40][41], YOLO [36][37][38]42,43] have been used, while new models such as lean CNN [44] and convolutional recurrent neural network (CRNN) [45] are also being developed.…”

Section: Related Workmentioning

confidence: 99%

“…In particular, the centered scale method showed an accuracy of 87% and was found to be the best classification model. AI-based object detection and distance estimation have also focused on pedestrian protection, serving as key techniques for computer vision-based pedestrian detection (PD) and distance estimation (DE) [34,35]. Dai et al [40] proposed a 'novel multi-task Fast R-CNN' that simultaneously conducts distance estimation and pedestrian detection using improved ResNet-50 architecture with a processing speed of 7 FPS and with pedestrian detection accuracy of more than 80%.…”

Section: Related Workmentioning

confidence: 99%

The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

As automated vehicles have been considered one of the important trends in intelligent transportation systems, various research is being conducted to enhance their safety. In particular, the importance of technologies for the design of preventive automated driving systems, such as detection of surrounding objects and estimation of distance between vehicles. Object detection is mainly performed through cameras and LiDAR, but due to the cost and limits of LiDAR’s recognition distance, the need to improve Camera recognition technique, which is relatively convenient for commercialization, is increasing. This study learned convolutional neural network (CNN)-based faster regions with CNN (Faster R-CNN) and You Only Look Once (YOLO) V2 to improve the recognition techniques of vehicle-mounted monocular cameras for the design of preventive automated driving systems, recognizing surrounding vehicles in black box highway driving videos and estimating distances from surrounding vehicles through more suitable models for automated driving systems. Moreover, we learned the PASCAL visual object classes (VOC) dataset for model comparison. Faster R-CNN showed similar accuracy, with a mean average precision (mAP) of 76.4 to YOLO with a mAP of 78.6, but with a Frame Per Second (FPS) of 5, showing slower processing speed than YOLO V2 with an FPS of 40, and a Faster R-CNN, which we had difficulty detecting. As a result, YOLO V2, which shows better performance in accuracy and processing speed, was determined to be a more suitable model for automated driving systems, further progressing in estimating the distance between vehicles. For distance estimation, we conducted coordinate value conversion through camera calibration and perspective transform, set the threshold to 0.7, and performed object detection and distance estimation, showing more than 80% accuracy for near-distance vehicles. Through this study, it is believed that it will be able to help prevent accidents in automated vehicles, and it is expected that additional research will provide various accident prevention alternatives such as calculating and securing appropriate safety distances, depending on the vehicle types.

show abstract

Deep Learning Based Dynamic Object Addition to Video Instances for Creating Synthetic Data

Chinthada¹,

Adarsh²

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

ROS-Based Pedestrian Detection and Distance Estimation Algorithm Using Stereo Vision, Leddar and CNN

Cited by 6 publications

References 14 publications

Reconocimiento y estimación de posición relativa de objetos en entornos controlados

Reconocimiento y estimación de posición relativa de objetos en entornos controlados

The Design of Preventive Automated Driving Systems Based on Convolutional Neural Network

Deep Learning Based Dynamic Object Addition to Video Instances for Creating Synthetic Data

Contact Info

Product

Resources

About