Near Zone Pedestrian Detection using a Low-Resolution FIR Sensor
J.-E. Källhammer, D. Eriksson, G. Granlund, M. Felsberg, A. Moe, B. Johansson, J. Wiklund, P.-E. ForssénIV07, Istanbul, Turkey
Intelligent Vehicles Symposium (IV'07)
June 2007
Abstract
This paper explores the possibility to use a single low-resolution FIR camera for detection of pedestrians in the near zone in front of a vehicle. A low resolution sensor reduces the cost of the system, as well as the amount of data that needs to be processed in each frame. We present a system that makes use of hot-spots and image positions of a near constant bearing to detect potential pedestrians. These detections provide seeds for an energy minimization algorithm that fits a pedestrian model to the detection. Since false alarms are hard to tolerate, the pedestrian model is then tracked, and the distance-to-collision (DTC) is measured by integrating size change measurements at sub-pixel accuracy, and the car velocity. The system should only engage braking for detections on a collision course, with a reliably measured DTC. Preliminary experiments on a number of recorded near collision sequences indicate that our method may be useful for ranges up to about 10m using an 80x60 sensor, and somewhat more using a 160x120 sensor. We also analyze the robustness of the evaluated algorithm with respect to dead pixels, a potential problem for low-resolution sensors.
Full Paper
On-line proceedings available from IEEE Xplore.
Bibtex entry
@InProceedings{kegfmjwf07, author = {J.-E. K\"allhammer and D. Eriksson and G. Granlund and M. Felsberg and A. Moe and B. Johansson and J. Wiklund and P.-E. Forss\'en}, title = {Near Zone Pedestrian Detection using a Low-Resolution FIR Sensor}, booktitle = {Intelligent Vehicles Symposium (IV'07)}, OPTpages = {}, year = {2007}, OPTeditor = {}, OPTvolume = {}, OPTnumber = {}, OPTseries = {}, address = {Istanbul, Turkey}, month = {June}, isbn = {1-4244-1067-3}, issn = {1931-0587}, organization = {{IEEE} Intelligent Transportation Systems Society}, publisher = {{IEEE}} }
Per-Erik Forssén
Contact:
Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654
< >
My pages:
Page responsible: Per-Erik Forssén
Last updated: 2024-09-28