AI SearchAnalysis of traffic data using the image processing approach
Call Number: AIT Thesis no.GT-91-36 Material type:
TextSeries: Asian Institute of Technology. Thesis ; no. GT-91-36Publication details: Bangkok : Asian Institute of Technology, 1992Description: 131 p. : illSubject(s): Online resources: Dissertation note: Thesis (M.Eng.) - Asian Institute of Technology Summary: This research concentrates on traffic data collection , headway, vehicle speed, lane changing and vehicle classification by video recording using image processing to extract these data automatically. This developed algorithm is applicable to moving vehicles. The overall procedure is separated into two major parts: image extraction and traffic characteristics extraction. The former employed the interframe technique modified from Vieren ' s method (1991 ) to obtain a binary image. The latter part is developed to extract traffic data from the former procedure. Two detection lines are set across a lane to detect brightness along the lines and data from these two lines were matched by the developed algorithm . Thanks to grouping and group matching techniques in this part , they can reduce many errors before finding the vehicle speeds . The result is good for speed study on expressway in Bangkok, the error of average travel speed about ±3 % while comparing with manual extraction. This algorithm was implemented as nonreal time. Time required by a personal computer to process a sequence of images was 25 times slower than real time. The detection rate is 5 frames per second by this machine, which can cause misdetecting. However, a grouping technique and a matching technique are proposed to reduce the error satisfactorily.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
22-AIT Thesis (Replacement)
|
Asian Institute of Technology Library AIT Publications | AIT Thesis no.GT-91-36 (Browse shelf(Opens below)) | 3 | Available | 30050120713036 | |||||||||||||
40-Archives
|
Asian Institute of Technology Library Archives | AIT Thesis no.GT-91-36 (Browse shelf(Opens below)) | 1 | Available | 30050120308811 |
Thesis (M.Eng.) - Asian Institute of Technology
A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Engineering and Technology
This research concentrates on traffic data collection , headway, vehicle speed, lane changing and vehicle classification by video recording using image processing to extract these data automatically. This developed algorithm is applicable to moving vehicles. The overall procedure is separated into two major parts: image extraction and traffic characteristics extraction. The former employed the interframe technique modified from Vieren ' s method (1991 ) to obtain a binary image. The latter part is developed to extract traffic data from the former procedure. Two detection lines are set across a lane to detect brightness along the lines and data from these two lines were matched by the developed algorithm . Thanks to grouping and group matching techniques in this part , they can reduce many errors before finding the vehicle speeds . The result is good for speed study on expressway in Bangkok, the error of average travel speed about ±3 % while comparing with manual extraction. This algorithm was implemented as nonreal time. Time required by a personal computer to process a sequence of images was 25 times slower than real time. The detection rate is 5 frames per second by this machine, which can cause misdetecting. However, a grouping technique and a matching technique are proposed to reduce the error satisfactorily.
There are no comments on this title.