Shadow detection and removal for traffic images

J. M. Wang, Y. C. Chung, C. L. Chang, S. W. Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

72 Citations (Scopus)

Abstract

Shadow detection and removal is an important task when dealing with outdoor images. Shadows cast by objects together with the objects form distorted figures. Furthermore, separate objects can be connected through shadows. Both can confuse object recognition systems. In this paper, an effective method is presented for detecting and removing shadows from foreground figures. We assume that foreground figures have been extracted from the input image by some background subtraction method. A figure may contain an object with or without shadow or multiple objects connected by shadows. To begin, we decide whether there are shadows in a given figure. A method based on illumination assessment is developed for this purpose. Once shadows have been confirmed existing in the given figure, their locations and orientations are estimated. A number of points are then sampled from the shadow candidates, from which attributes of shadow are computed. We do not remove shadows simply based on the computed attributes. The reason is twofold. First, the distribution of intensity within a shadow is not uniform. Second, shadows can be divided into cast and self shadows; only cast shadows are to be removed. To deal with the first issue, we recover object shapes progressively instead of directly removing shadows. The second issue is resolved based on the observation that self shadows possess denser distributions of texture than cast shadows in our application. A number of experiments have been performed. The results revealed the applicability of the proposed technique.

Original languageEnglish
Title of host publicationConference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control
Pages649-654
Number of pages6
Publication statusPublished - 2004 Jun 28
EventConference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control - Taipei, Taiwan
Duration: 2004 Mar 212004 Mar 23

Publication series

NameConference Proceeding - IEEE International Conference on Networking, Sensing and Control
Volume1

Other

OtherConference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control
CountryTaiwan
CityTaipei
Period04/3/2104/3/23

Fingerprint

Object recognition
Textures
Lighting
Experiments

Keywords

  • Shadow detection
  • Shadow removal
  • Vehicle detection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Wang, J. M., Chung, Y. C., Chang, C. L., & Chen, S. W. (2004). Shadow detection and removal for traffic images. In Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control (pp. 649-654). (Conference Proceeding - IEEE International Conference on Networking, Sensing and Control; Vol. 1).

Shadow detection and removal for traffic images. / Wang, J. M.; Chung, Y. C.; Chang, C. L.; Chen, S. W.

Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. 2004. p. 649-654 (Conference Proceeding - IEEE International Conference on Networking, Sensing and Control; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, JM, Chung, YC, Chang, CL & Chen, SW 2004, Shadow detection and removal for traffic images. in Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. Conference Proceeding - IEEE International Conference on Networking, Sensing and Control, vol. 1, pp. 649-654, Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control, Taipei, Taiwan, 04/3/21.
Wang JM, Chung YC, Chang CL, Chen SW. Shadow detection and removal for traffic images. In Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. 2004. p. 649-654. (Conference Proceeding - IEEE International Conference on Networking, Sensing and Control).
Wang, J. M. ; Chung, Y. C. ; Chang, C. L. ; Chen, S. W. / Shadow detection and removal for traffic images. Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. 2004. pp. 649-654 (Conference Proceeding - IEEE International Conference on Networking, Sensing and Control).
@inproceedings{05adac80bc3e4a41a20fdc3af7afb805,
title = "Shadow detection and removal for traffic images",
abstract = "Shadow detection and removal is an important task when dealing with outdoor images. Shadows cast by objects together with the objects form distorted figures. Furthermore, separate objects can be connected through shadows. Both can confuse object recognition systems. In this paper, an effective method is presented for detecting and removing shadows from foreground figures. We assume that foreground figures have been extracted from the input image by some background subtraction method. A figure may contain an object with or without shadow or multiple objects connected by shadows. To begin, we decide whether there are shadows in a given figure. A method based on illumination assessment is developed for this purpose. Once shadows have been confirmed existing in the given figure, their locations and orientations are estimated. A number of points are then sampled from the shadow candidates, from which attributes of shadow are computed. We do not remove shadows simply based on the computed attributes. The reason is twofold. First, the distribution of intensity within a shadow is not uniform. Second, shadows can be divided into cast and self shadows; only cast shadows are to be removed. To deal with the first issue, we recover object shapes progressively instead of directly removing shadows. The second issue is resolved based on the observation that self shadows possess denser distributions of texture than cast shadows in our application. A number of experiments have been performed. The results revealed the applicability of the proposed technique.",
keywords = "Shadow detection, Shadow removal, Vehicle detection",
author = "Wang, {J. M.} and Chung, {Y. C.} and Chang, {C. L.} and Chen, {S. W.}",
year = "2004",
month = "6",
day = "28",
language = "English",
isbn = "0780381939",
series = "Conference Proceeding - IEEE International Conference on Networking, Sensing and Control",
pages = "649--654",
booktitle = "Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control",

}

TY - GEN

T1 - Shadow detection and removal for traffic images

AU - Wang, J. M.

AU - Chung, Y. C.

AU - Chang, C. L.

AU - Chen, S. W.

PY - 2004/6/28

Y1 - 2004/6/28

N2 - Shadow detection and removal is an important task when dealing with outdoor images. Shadows cast by objects together with the objects form distorted figures. Furthermore, separate objects can be connected through shadows. Both can confuse object recognition systems. In this paper, an effective method is presented for detecting and removing shadows from foreground figures. We assume that foreground figures have been extracted from the input image by some background subtraction method. A figure may contain an object with or without shadow or multiple objects connected by shadows. To begin, we decide whether there are shadows in a given figure. A method based on illumination assessment is developed for this purpose. Once shadows have been confirmed existing in the given figure, their locations and orientations are estimated. A number of points are then sampled from the shadow candidates, from which attributes of shadow are computed. We do not remove shadows simply based on the computed attributes. The reason is twofold. First, the distribution of intensity within a shadow is not uniform. Second, shadows can be divided into cast and self shadows; only cast shadows are to be removed. To deal with the first issue, we recover object shapes progressively instead of directly removing shadows. The second issue is resolved based on the observation that self shadows possess denser distributions of texture than cast shadows in our application. A number of experiments have been performed. The results revealed the applicability of the proposed technique.

AB - Shadow detection and removal is an important task when dealing with outdoor images. Shadows cast by objects together with the objects form distorted figures. Furthermore, separate objects can be connected through shadows. Both can confuse object recognition systems. In this paper, an effective method is presented for detecting and removing shadows from foreground figures. We assume that foreground figures have been extracted from the input image by some background subtraction method. A figure may contain an object with or without shadow or multiple objects connected by shadows. To begin, we decide whether there are shadows in a given figure. A method based on illumination assessment is developed for this purpose. Once shadows have been confirmed existing in the given figure, their locations and orientations are estimated. A number of points are then sampled from the shadow candidates, from which attributes of shadow are computed. We do not remove shadows simply based on the computed attributes. The reason is twofold. First, the distribution of intensity within a shadow is not uniform. Second, shadows can be divided into cast and self shadows; only cast shadows are to be removed. To deal with the first issue, we recover object shapes progressively instead of directly removing shadows. The second issue is resolved based on the observation that self shadows possess denser distributions of texture than cast shadows in our application. A number of experiments have been performed. The results revealed the applicability of the proposed technique.

KW - Shadow detection

KW - Shadow removal

KW - Vehicle detection

UR - http://www.scopus.com/inward/record.url?scp=2942642051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942642051&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:2942642051

SN - 0780381939

T3 - Conference Proceeding - IEEE International Conference on Networking, Sensing and Control

SP - 649

EP - 654

BT - Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control

ER -