The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Di antara aplikasi ITS, adalah sangat penting untuk memperoleh statistik terperinci aliran trafik. Untuk tujuan itu, penderia penglihatan mempunyai kelebihan kerana maklumatnya yang kaya berbanding dengan penderia titik tersebut seperti pengesan gelung atau penderia gelombang supersonik. Walau bagaimanapun, selama bertahun-tahun, pengesanan kenderaan dalam imej trafik telah mengalami masalah kesan oklusi dan kesan pencahayaan. Untuk menyelesaikan masalah oklusi, kami telah mencadangkan model Spatio-Temporal Markov Random Field(ST MRF) untuk pembahagian imej Spatio-Temporal. Model ST MRF ini mengoptimumkan sempadan pembahagian kenderaan tersumbat dan vektor gerakannya secara serentak dengan merujuk kepada tekstur dan korelasi pelabelan segmen di sepanjang paksi temporal serta paksi ruang. Akibatnya, ST MRF telah terbukti berjaya untuk pengesanan kenderaan walaupun terhadap oklusi teruk yang ditemui dalam imej trafik sudut rendah dengan gerakan yang rumit, seperti di persimpangan lebuh raya. Di samping itu, dalam kertas ini, kami mentakrifkan kaedah untuk mendapatkan imej invarian pencahayaan dengan menganggar tenaga MRF di antara keamatan piksel jiran. Imej pencahayaan-invarian ini sangat stabil walaupun perubahan mendadak dalam pencahayaan atau kesan teduhan berlaku dalam imej asal. Kami kemudiannya berjaya menyepadukan kaedah untuk imej tenaga MRF dengan lancar ke dalam model ST MRF kami. Oleh itu, pengesanan kenderaan telah berjaya dilakukan oleh ST MRF, walaupun terhadap variasi pencahayaan yang mendadak dan terhadap kesan teduhan . Akhir sekali, untuk mengesahkan keberkesanan algoritma penjejakan kami berdasarkan ST MRF untuk kegunaan praktikal, kami membangunkan sistem automatik untuk memperoleh statistik trafik daripada aliran imej trafik. Sistem ini telah beroperasi secara berterusan selama sepuluh bulan, dan dengan itu keberkesanan algoritma pengesanan berdasarkan model ST MRF telah terbukti.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Shunsuke KAMIJO, Tsunetoshi NISHIDA, Masao SAKAUCHI, "Occlusion Robust and Illumination Invariant Vehicle Tracking for Acquiring Detailed Statistics from Traffic Images" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 11, pp. 1753-1766, November 2002, doi: .
Abstract: Among ITS applications, it is very important to acquire detailed statistics of traffic flows. For that purpose, vision sensors have an advantage because of their rich information compared to such spot sensors such as loop detectors or supersonic wave sensors. However, for many years, vehicle tracking in traffic images has suffered from the problems of occlusion effect and illumination effect. In order to resolve occlusion problems, we have been proposing the Spatio-Temporal Markov Random Field model(S-T MRF) for segmentation of Spatio-Temporal images. This S-T MRF model optimizes the segmentation boundaries of occluded vehicles and their motion vectors simultaneously by referring to textures and segment labeling correlations along the temporal axis as well as the spatial axis. Consequently, S-T MRF has been proven to be successful for vehicle tracking even against severe occlusions found in low-angle traffic images with complicated motions, such at highway junctions. In addition, in this paper, we define a method for obtaining illumination-invariant images by estimating MRF energy among neighbor pixel intensities. These illumination-invariant images are very stable even when sudden variations in illumination or shading effect are occurred in the original images. We then succeeded in seamlessly integrating the method for MRF energy images into our S-T MRF model. Thus, vehicle tracking was performed successfully by S-T MRF, even against sudden variations in illumination and against shading effects . Finally, in order to verify the effectiveness of our tracking algorithm based on the S-T MRF for practical uses, we developed an automated system for acquiring traffic statistics out of a flow of traffic images. This system has been operating continuously for ten months, and thus effectiveness of the tracking algorithm based on S-T MRF model was proven.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_11_1753/_p
Salinan
@ARTICLE{e85-d_11_1753,
author={Shunsuke KAMIJO, Tsunetoshi NISHIDA, Masao SAKAUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Occlusion Robust and Illumination Invariant Vehicle Tracking for Acquiring Detailed Statistics from Traffic Images},
year={2002},
volume={E85-D},
number={11},
pages={1753-1766},
abstract={Among ITS applications, it is very important to acquire detailed statistics of traffic flows. For that purpose, vision sensors have an advantage because of their rich information compared to such spot sensors such as loop detectors or supersonic wave sensors. However, for many years, vehicle tracking in traffic images has suffered from the problems of occlusion effect and illumination effect. In order to resolve occlusion problems, we have been proposing the Spatio-Temporal Markov Random Field model(S-T MRF) for segmentation of Spatio-Temporal images. This S-T MRF model optimizes the segmentation boundaries of occluded vehicles and their motion vectors simultaneously by referring to textures and segment labeling correlations along the temporal axis as well as the spatial axis. Consequently, S-T MRF has been proven to be successful for vehicle tracking even against severe occlusions found in low-angle traffic images with complicated motions, such at highway junctions. In addition, in this paper, we define a method for obtaining illumination-invariant images by estimating MRF energy among neighbor pixel intensities. These illumination-invariant images are very stable even when sudden variations in illumination or shading effect are occurred in the original images. We then succeeded in seamlessly integrating the method for MRF energy images into our S-T MRF model. Thus, vehicle tracking was performed successfully by S-T MRF, even against sudden variations in illumination and against shading effects . Finally, in order to verify the effectiveness of our tracking algorithm based on the S-T MRF for practical uses, we developed an automated system for acquiring traffic statistics out of a flow of traffic images. This system has been operating continuously for ten months, and thus effectiveness of the tracking algorithm based on S-T MRF model was proven.},
keywords={},
doi={},
ISSN={},
month={November},}
Salinan
TY - JOUR
TI - Occlusion Robust and Illumination Invariant Vehicle Tracking for Acquiring Detailed Statistics from Traffic Images
T2 - IEICE TRANSACTIONS on Information
SP - 1753
EP - 1766
AU - Shunsuke KAMIJO
AU - Tsunetoshi NISHIDA
AU - Masao SAKAUCHI
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2002
AB - Among ITS applications, it is very important to acquire detailed statistics of traffic flows. For that purpose, vision sensors have an advantage because of their rich information compared to such spot sensors such as loop detectors or supersonic wave sensors. However, for many years, vehicle tracking in traffic images has suffered from the problems of occlusion effect and illumination effect. In order to resolve occlusion problems, we have been proposing the Spatio-Temporal Markov Random Field model(S-T MRF) for segmentation of Spatio-Temporal images. This S-T MRF model optimizes the segmentation boundaries of occluded vehicles and their motion vectors simultaneously by referring to textures and segment labeling correlations along the temporal axis as well as the spatial axis. Consequently, S-T MRF has been proven to be successful for vehicle tracking even against severe occlusions found in low-angle traffic images with complicated motions, such at highway junctions. In addition, in this paper, we define a method for obtaining illumination-invariant images by estimating MRF energy among neighbor pixel intensities. These illumination-invariant images are very stable even when sudden variations in illumination or shading effect are occurred in the original images. We then succeeded in seamlessly integrating the method for MRF energy images into our S-T MRF model. Thus, vehicle tracking was performed successfully by S-T MRF, even against sudden variations in illumination and against shading effects . Finally, in order to verify the effectiveness of our tracking algorithm based on the S-T MRF for practical uses, we developed an automated system for acquiring traffic statistics out of a flow of traffic images. This system has been operating continuously for ten months, and thus effectiveness of the tracking algorithm based on S-T MRF model was proven.
ER -