Title :
Direction estimation of pedestrian from multiple still images
Author :
Shimizu, Hiroaki ; Poggio, Tomaso
Author_Institution :
Toyota Odaiba Lab., Toyota Motor Corp., Japan
Abstract :
The capability of estimating the walking direction of pedestrian would be useful in many applications such as those involving autonomous vehicles. We introduce an approach for estimating the walking direction of pedestrian from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier. Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance.
Keywords :
feature extraction; image classification; image sequences; mobile robots; motion estimation; support vector machines; vehicles; SVM; autonomous vehicles; feature extraction; image classification; multiple still images; pedestrian walking direction estimation; system performance; walking sequence; Biological system modeling; Face detection; Histograms; Humans; Image segmentation; Legged locomotion; Pixel; Shape; Support vector machines; Wavelet coefficients;
Conference_Titel :
Intelligent Vehicles Symposium, 2004 IEEE
Print_ISBN :
0-7803-8310-9
DOI :
10.1109/IVS.2004.1336451