Multi-view and multi-plane data fusion for effective pedestrian detection in intelligent visual surveillance

Ren, Jie; Xu, Ming; Smith, Jeremy S.; Cheng, Shi

doi:10.1007/s11045-016-0428-x

Cited by 10 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features extraction aims at object detection or tracking, and post-processing involves different learning or matching based techniques for computing inter-view correlations and final summary generation. The final generated summary is useful in many applications [13][14][15] including indoor and outdoor CCTV automatic monitoring [16] for activities and events detection [17]. Furthermore, it can be utilized for post-accident scenarios investigation, retrieval applications, and the salient information can assist in many diverse domains such as law enforcements, sports, and entertainment.…”

mentioning

confidence: 99%

Cloud-Assisted Multiview Video Summarization Using CNN and Bidirectional LSTM

Hussain

Muhammad

Ullah

et al. 2020

IEEE Trans. Ind. Inf.

124

View full text Add to dashboard Cite

The massive amount of video data produced by surveillance networks in industries instigate various challenges in exploring these videos for many applications such as video summarization (VS), analysis, indexing, and retrieval. The task of multi-view video summarization (MVS) is very challenging due to the gigantic size of data, redundancy, overlapping in views, light variations, and inter-view correlations. To address these challenges, various low-level features and clustering based soft computing techniques are proposed that cannot fully exploit MVS. In this article, we achieve MVS by integrating deep neural network based soft computing techniques in a two tier framework. The first online tier performs target appearance based shots segmentation and stores them in a lookup table that is transmitted to cloud for further processing. The second tier extracts deep features from each frame of a sequence in the lookup table and pass them to deep bi-directional long short-term memory (DB-LSTM) to acquire probabilities of informativeness and generate a summary. Experimental 1 evaluation on benchmark dataset and industrial surveillance data from YouTube confirms the better performance of our system compared to state-of-the-art MVS.

show abstract

mentioning

confidence: 99%

Cloud-Assisted Multiview Video Summarization Using CNN and Bidirectional LSTM

Hussain

Muhammad

Ullah

et al. 2020

IEEE Trans. Ind. Inf.

124

View full text Add to dashboard Cite

show abstract

“…The homography, from the top view to camera view c , for the ground plane is [27]

{bold-italicH}_{g}^{t, c} = false({bold-italicH}_{g}^{c, t} {false)}^{- 1} = false[{bold-italicm}_{1}, {bold-italicm}_{2}, {bold-italicm}_{4} false] .

The homography, from the top view to camera view c , for the plane parallel to the ground plane and at a height of h is as follows [27], where

false[0 false]

is a

3 \times 2

zero matrix:

{bold-italicH}_{h}^{t, c} = false[{bold-italicm}_{1}, {bold-italicm}_{2}, h {bold-italicm}_{3} + {bold-italicm}_{4} false] = {bold-italicH}_{g}^{t, c} + false[0 | h {bold-italicm}_{3} false] .

…”

Section: Homography Estimationmentioning

confidence: 99%

“…The homography, from the top view to camera view c, for the plane parallel to the ground plane and at a height of h is as follows [27], where [0] is a 3 × 2 zero matrix:…”

Section: Homography Estimation With Calibrated Camerasmentioning

confidence: 99%

Moving shadow detection via binocular vision and colour clustering

Lü

Smith³

et al. 2020

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

A pedestrian segmentation algorithm in the presence of cast shadows is presented in this study. The novelty of this algorithm lies in the fusion of multi‐view and multi‐plane homographic projections of foregrounds and the use of the fused data to guide colour clustering. This brings about an advantage over the existing binocular algorithms in that it can remove cast shadows while keeping pedestrians’ body parts, which occlude shadows. Phantom detection, which is inherent with the binocular method, is also investigated. Experimental results with real‐world videos have demonstrated the efficiency of this algorithm.

show abstract