ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Shadow Detection and Removal from Moving Object Using Neuro-Fuzzy

Journal: International Journal for Research in Engineering Application & Management (Vol.03, No. 10)

Publication Date:

Authors : ;

Page : 18-21

Keywords : Neuro Fuzzy; recognition; Shadow detection; tracking object; stereo;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Detection and tracking of moving objects is at the core of many applications dealing with image sequences. One of the main challenges in these applications is identifying shadows which objects cast and which move along with them in the scene. Shadows cause serious problems while segmenting and extracting moving objects due to the misclassification of shadow points as foreground. Shadows can cause object merging, object shape distortion, and even object losses (due to the shadow cast over another object). The difficulties associated with shadow detection arise since shadows and objects share two important visual features. First, shadow points are detectable as foreground points since they typically differ significantly from the background. Second, shadows have the same motion as the objects casting them. For this reason, the shadow identification is critical both for still images and for image sequences (video) and has become an active research area, especially in the recent past. It should be noted that, while the main concepts utilized for shadow analysis in still and video images are similar, typically, the purpose behind shadow extraction is somewhat different. Our goal is to build a reliable shadow detector for moving objects of outdoor scenes. While detecting all shadows is expected to remain hard, we explicitly focus on the shadows cast by objects onto the ground plane. The types of materials constituting the ground in typical outdoor scenes are (relatively) limited, most commonly including concrete, asphalt, grass, mud, stone, brick, etc. With this observation, our hypothesis is that the appearances of shadows on the ground are not as widely varying as the shadows everywhere in the scene and can be learned from a set of labeled images of real world scenes. This restriction by no means makes the problem trivial: the ground shadow detector still needs to contend with myriad other non-shadow visual manifestations such as markings and potholes on the roads, pavement/road boundaries, grass patterns on lawns, etc. Further, since many objects (pedestrians, vehicles, traffic signs, etc) of interest to vision applications, are attached to the ground and cast shadows onto the ground, we believe such a ground shadow detector will find wide applicability.

Last modified: 2018-01-13 12:20:41