Real-time pedestrian detection with the videos of car camera
Pedestrians in the vehicle path are in danger of being hit, thus causing severe injury to pedestrians and vehicle occupants. Therefore, real-time pedestrian detection with the video of vehicle-mounted camera is of great significance to vehicle–pedestrian collision warning and traffic safety of self-...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SAGE Publishing
2015-12-01
|
Series: | Advances in Mechanical Engineering |
Online Access: | https://doi.org/10.1177/1687814015622903 |
id |
doaj-b66ce19626a3426c933adbf20ed944e4 |
---|---|
record_format |
Article |
spelling |
doaj-b66ce19626a3426c933adbf20ed944e42020-11-25T03:43:56ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402015-12-01710.1177/168781401562290310.1177_1687814015622903Real-time pedestrian detection with the videos of car cameraYunling Zhang0Guofeng Wang1Xingfa Gu2Shaoming Zhang3Jianping Hu4Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, ChinaInstitute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, ChinaInstitute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, ChinaDepartment of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaDepartment of Surveying and Geo-Informatics, Tongji University, Shanghai, ChinaPedestrians in the vehicle path are in danger of being hit, thus causing severe injury to pedestrians and vehicle occupants. Therefore, real-time pedestrian detection with the video of vehicle-mounted camera is of great significance to vehicle–pedestrian collision warning and traffic safety of self-driving car. In this article, a real-time scheme was proposed based on integral channel features and graphics processing unit. The proposed method does not need to resize the input image. Moreover, the computationally expensive convolution of the detectors and the input image was converted into the dot product of two larger matrixes, which can be computed effectively using a graphics processing unit. The experiments showed that the proposed method could be employed to detect pedestrians in the video of car camera at 20+ frames per second with acceptable error rates. Thus, it can be applied in real-time detection tasks with the videos of car camera.https://doi.org/10.1177/1687814015622903 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yunling Zhang Guofeng Wang Xingfa Gu Shaoming Zhang Jianping Hu |
spellingShingle |
Yunling Zhang Guofeng Wang Xingfa Gu Shaoming Zhang Jianping Hu Real-time pedestrian detection with the videos of car camera Advances in Mechanical Engineering |
author_facet |
Yunling Zhang Guofeng Wang Xingfa Gu Shaoming Zhang Jianping Hu |
author_sort |
Yunling Zhang |
title |
Real-time pedestrian detection with the videos of car camera |
title_short |
Real-time pedestrian detection with the videos of car camera |
title_full |
Real-time pedestrian detection with the videos of car camera |
title_fullStr |
Real-time pedestrian detection with the videos of car camera |
title_full_unstemmed |
Real-time pedestrian detection with the videos of car camera |
title_sort |
real-time pedestrian detection with the videos of car camera |
publisher |
SAGE Publishing |
series |
Advances in Mechanical Engineering |
issn |
1687-8140 |
publishDate |
2015-12-01 |
description |
Pedestrians in the vehicle path are in danger of being hit, thus causing severe injury to pedestrians and vehicle occupants. Therefore, real-time pedestrian detection with the video of vehicle-mounted camera is of great significance to vehicle–pedestrian collision warning and traffic safety of self-driving car. In this article, a real-time scheme was proposed based on integral channel features and graphics processing unit. The proposed method does not need to resize the input image. Moreover, the computationally expensive convolution of the detectors and the input image was converted into the dot product of two larger matrixes, which can be computed effectively using a graphics processing unit. The experiments showed that the proposed method could be employed to detect pedestrians in the video of car camera at 20+ frames per second with acceptable error rates. Thus, it can be applied in real-time detection tasks with the videos of car camera. |
url |
https://doi.org/10.1177/1687814015622903 |
work_keys_str_mv |
AT yunlingzhang realtimepedestriandetectionwiththevideosofcarcamera AT guofengwang realtimepedestriandetectionwiththevideosofcarcamera AT xingfagu realtimepedestriandetectionwiththevideosofcarcamera AT shaomingzhang realtimepedestriandetectionwiththevideosofcarcamera AT jianpinghu realtimepedestriandetectionwiththevideosofcarcamera |
_version_ |
1724517351215333376 |