Automatic vehicle detection systems in urban and inter-urban traffic using computer vision are frequently based on background subtraction methods. Moving shadows represent a serious difficulty for these methods, as they will appear as part of the segmented foreground vehicles. Shadow removal algorithms usually rely on exploiting color properties. However, the use of image color information, when available, is more computationally demanding and it may compromise many real-time implementations. This paper proposes a shadow removal algorithm, suitable for background subtraction methods, where only grayscale information is required. The method is based on edge density computation on a quotient image, obtained from the current frame and the background model. Experimental results from various traffic scenes are provided in order to prove the validity of the proposed method.
PurposeIntelligent transportation systems (ITS) are defined as new infrastructures that combine people, roads and vehicles over the basis of modern embedded systems with enhanced digital connectivity. ITS is fast becoming a reality, favored in their development by the use of the internet. The purpose of this paper is to analyze the feasibility of road‐traffic management systems, using the internet as the communication link.Design/methodology/approachA literature review is presented to give a background in the progressive role that ITS and road safety and control applications play in society. The combination of internet and the ITS architecture is covered, and an electronic prototype providing web services for road‐traffic management is designed as an example. The scope of road traffic security research is extensive, and the use of artificial vision systems in road‐traffic analysis (technology which is on the basis of the developed prototype) is also discussed. The hardware and software characteristics of the prototype are defined.FindingsThe paper provides new insights into the use of the internet for road‐traffic management applications.Research limitations/implicationsThe research is limited to one particular road‐traffic management system. Results could be extended if more real equipments were analyzed. Also, end‐users' perception and their acceptance of the new technology could be examined using an information system theory like the technology acceptance model.Originality/valueThe paper shows the utility of the internet in the development of novel ITS.
This paper proposes an enhanced version of the sigma delta background estimation method, suitable for urban traffic scenes. In the original algorithm, the background model quickly degrades in such complex scenes, being easily contaminated by slow moving or temporarily stopped vehicles. Some heuristics have been added to the basic algorithm in order to make a selective background model updating at the pixel level. Experimental tests made over typical urban traffic streams prove the validity of the proposed enhanced version.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.