preview

Dynamic Threshold Value for the Traffic Lane Extraction

explanatory Essay
2003 words
2003 words
bookmark

Executive Summary This project is to find out the dynamic threshold value for the traffic lane extraction . At the early stage, we found that the threshold value of the image was the main item we had to solve. This is because the threshold value of the image can provide us the better image on the traffic lane extraction. Dynamic threshold value determination is to produce a continuous threshold value to the traffic lane extraction. By using the LabVIEW Program, we can easily extract the light intensity and HSI data of the image and get the threshold value by comparing the data with the threshold value database. Table of Contents No. Description Page A. Introduction…………………………………………………………. 3 B. Literature Search………………………………………………………………….. 3 C. Design Concept……………………………………………………………. 4 D. Block Diagram………………………………………………………. 4 E. Experimental Record ………………………………………………………………… 5 F. Project Timeline…………………………………………………………………… 6 G. Result and Conclusion…………………………………………………………… H. References……………………………………………………………………. 7 A. INTRODUCTION Since the 21st Century, Autonomous vehicles are the hit topics in the world which is very important on the Intelligent Transport System. The basic provision of the intelligent vehicles should provide the information of route direction, sense objects or pedestrians; prevent impending collisions and lane departure warning to the driver. The benefits of autonomous vehicles are: a. Reduce traffic collisions – autonomous vehicles increase reliability and quick respond time compare with human. b. Fewer traffic congestion and enlarge roadway capacity – the safety gaps between vehicles area are reduced and better traffic flow management. c. Higher speed limit. d. Alleviatio... ... middle of paper ... ...ngbill, David Lieb and Sebastian Thrun, “Optical Flow Approaches for Self-supervised Learning in Autonomous Mobile Robot Navigation”, Autonomous Navigation in Dynamic Environments, 2007 [5] Shengyan Zhou, Yanhua Jiang, “ A Novel Lane Detection based on Geometrical Model and Gabor Filter”,2010 IEEE Intelligent Vehicles Symposium, pp.59-64, Jun, 2010 [6] J.M. A’ lvarez and A. Lo’pez, “Novel Index for Objective Evaluation of Road Detection Algorithms”, In Proc. of the IEEE Intelligent Transportation System, Oct. 2008. [7] Yue Wang, Dinggang Shen and Eam Khwang Teoh, “Lane Detection Using Catmull-Rom Spline”, In Proc. of the IEEE IntelligentVehicles, 1998 [8] Tsung-Ying Sun, Member, IEEE, Shang-Jeng Tsai and Vincent Chan, “HSI Color Model Based Lane-Marking Detection”, In Proc. of the IEEE Intelligent Transportation System Conference, pp. 1168-1172, September, 2006

In this essay, the author

  • Explains that this project is to find out the dynamic threshold value for the traffic lane extraction.
  • Explains that autonomous vehicles are the hit topics in the 21st century, which is very important on the intelligent transport system. the basic provision of intelligent vehicles should provide the information of route direction, sense objects or pedestrians, and prevent impending collisions.
  • Explains that autonomous vehicles reduce traffic collisions and increase reliability and quick response time.
  • Explains that less traffic congestion and enlarge roadway capacity reduce safety gaps between vehicles area and better traffic flow management.
  • Explains that the vehicles can park far away after drop off the passenger and return back as request by passenger.
  • Explains that lane and road, elimination of moving car by comparing the shape and size of the object, and.
  • Opines that lane-mark edges are used to detect a car's lanes, but this method relies on clear marks.
  • Explains that the detection images are transform to the lane models and compute the lanes. the complexity of computations for the transformation of models lowers the real time capability.
  • Explains that moving vehicles will eliminate by comparing the size and shape of the object.
  • Explains that lane coherence verification is the final step of line extraction, whereby the previously detected boundary width and orientation are stored.
  • Defines the region of interest (roi) in order to eliminate the un-used object.
  • Cites hsu-yung cheng, bor-shenn, pei-ting tseng, and kuo-chin fan in ieee transactions on the intelligent transportation system.
  • Cites claudio rosito jung and christian roberto keller in image and vision computing 23: 1192-1202, 2005.
  • Presents wei liu, hongliang zhang, bobo duan, huai yuan and hong zhao's "vision-based real-time lane marking detection and tracking", in ieee intelligent transportation system.
  • Presents andrew lookingbill, david lieb, and sebastian thrun's "optical flow approaches for self-supervised learning in autonomous mobile robot navigation".
  • Presents shengyan zhou and yanhua jiang's paper, "a novel lane detection based on geometrical model and gabor filter", ieee intelligent vehicles symposium.
  • Presents j.m. a’ lvarez and a. lo’pez's novel index for objective evaluation of road detecting algorithms.
  • Presents yue wang, dinggang shen, and eam khwang teoh, "lane detection using catmull-rom spline", in ieee intelligentvehicles, 1998.
  • Explains that tsung-ying sun, ieee member, shang-jeng tai, and vincent chan, "hsi color model based lane-marking detection", ieee intelligent transportation system conference.
  • Explains that at the early stage, the threshold value of the image was the main item they had to solve, because it can provide us the better image on the traffic lane extraction.
  • Explains the mechanism of lane departure warning system, which is designed to prevent the cost of accidents by driver error, distraction and drowsiness.
  • Explains the advantages of his color model-based lane-marking detection.
  • Explains that the early stage of the project is to develop the traffic lane detection and reconstruction system and provide the necessary information to the driver.
Get Access