Minnesota Department of Transportation, Office of Research & Strategic Services, 2000 - Automatic data collection systems - 23 pages
This report describes a system for monitoring bicycle activity in sequences of gray scale images from a stationary camera. Applications for such a system include determining the use and congestion of bicycle paths. The output of the system is a count of the number of bicycles detected in the image sequence. The system uses a simple model of two circular objects separated by relatively known distance, with four levels of abstraction: raw images, blobs, edge images, and the bicycle model. The system was implemented on a dual Pentium computer equipped with a Matrox imaging board and achieved a peak performance of eight frames per second. Experimental results based on outdoor scenes show promising results for a variety of weather conditions.
What people are saying - Write a review
We haven't found any reviews in the usual places.
GENERIC OBJECT TRACKING
HARDWARE FOR VISIONBASED DETECTION
1 other sections not shown
14 Figure algorithm background bicycle model bicycle path bicycle tires bicycle wheels bicycles detected bike BLOB EXTRACTION blob graph blobs and pairing blobs and radius border following camera is perpendicular center point computationally concem congestion cost function Department of Transportation detect bicycles detection of bicycles determine difﬁcult edge detection Edge subimage efﬁcient Example image false detection Figure 19 Figure 20 ﬁrst Hausdorff metric Hough blobs Hough transform image frame image from Lake image sequence Ireland Boulevard St John Ireland Lake Calhoun Minnesota Department Mn/DOT model matches monitoring bicycle activity multi-use trails number of bicycles object being tracked object tracking occlusions optical axis optimum graph overview parent structure constraint pedestrians Pentium computer equipped proposed system radius pairs raster scan raw images real-time reﬂect the views rollerbladers satisfy the parent segment sensors setup signiﬁcantly speciﬁc Thresholded edge image track bicycles trafﬁc objects velocity video cassette recorder weather conditions