TED: A texture-edge descriptor for pedestrian detection in video sequences

Armanfard, Narges; Komeili, Majid; Kabir, Ehsanollah

doi:10.1016/j.patcog.2011.08.010

Cited by 23 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the research works in motion segmentation have been attempted using the conventional background subtraction [5], statistical background subtraction [6][7][8][9][10], temporal differencing [11][12][13], optical flow [14] and hybrid [15][16][17][18][19][20][21] approaches.…”

Section: Literature Reviewmentioning

confidence: 99%

Cast and Self Shadow Segmentation in Video Sequences using Interval based Eigen Value Representation

Chandrajit¹,

Girisha²,

Vasudev³

et al. 2016

IJCA

View full text Add to dashboard Cite

Tracking of motion objects in the surveillance videos is useful for the monitoring and analysis. The performance of the surveillance system will deteriorate when shadows are detected as moving objects. Therefore, shadow detection and elimination usually benefits the next stages. To overcome this issue, a method for detection and elimination of shadows is proposed. This paper presents a method for segmenting moving objects in video sequences based on determining the Euclidian distance between two pixels considering neighborhood values in temporal domain. Further, a method that segments cast and self shadows in video sequences by computing the Eigen values for the neighborhood of each pixel is proposed. The dual-map for cast and self shadow pixels is represented based on the interval of Eigen values. The proposed methods are tested on the benchmark IEEE CHANGE DETECTION 2014 dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Cast and Self Shadow Segmentation in Video Sequences using Interval based Eigen Value Representation

Chandrajit¹,

Girisha²,

Vasudev³

et al. 2016

IJCA

View full text Add to dashboard Cite

show abstract

“…In our work, we obtained image features using TED [37], SUN [39], SURF [38], HOG [36], and Gist [27] image descriptors. Image feature dimension obtained through TED and SUN image descriptors are the same as that of the original image which we further reduced using I2A approach.…”

Section: Nearest Neighborhood Quality Measure and Optimal Image Reprementioning

confidence: 99%

“…We improved local neighborhood structure using maximum NNQ measure in order to achieve performance improvement for image datasets with significant within-class variation. We selected an optimal image descriptor among TED [37], SUN [39], SURF [38], HOG [36], and Gist [27]. For each image descriptor, we have shown simulation results of computing NNQ measure for each image dataset in Table 2 in which an overall NNQ measure on all image datasets is also shown.…”

Section: Nearest Neighborhood Quality Measure and Optimal Image Reprementioning

confidence: 99%

“…3 where some representative images from 6 out of 100 classes of AR [26] image database are shown that clearly show pose, illumination and occlusion variations in images of multimodal AR image datasets. For each image dataset, optimal image features are obtained using TED [37], SUN [39], SURF [38], HOG [36], and Gist [27] image descriptors and corresponding NNQ measure for each image descriptor is computed. Decision to choose best image descriptor among all image descriptors is performed on the basis of an overall maximum NNQ measure on all image databases.…”

Section: Nearest Neighborhood Quality Measure and Optimal Image Reprementioning

confidence: 99%

“…We improved local neighborhood structure based on maximum NNQ measure for k-nearest neighbor based approach by selecting an optimal image descriptor among recently reported image descriptors such as Histograms of Oriented Gradients (HOG) [35], [36], modeling the shape of the scene (Gist) [27], Texture Edge Descriptors (TED) [37], Speeded-up Robust Features (SURF) [38], and Saliency Using Natural Statistics (SUN) [39]. For each image descriptor, we obtained image features and computed corresponding NNQ measure, and obtained an overall NNQ measure on 10 image datasets.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multimode Image Clustering Using Optimal Image Descriptor

Ahmed

Jalil

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYManifold learning based image clustering models are usually employed at local level to deal with images sampled from nonlinear manifold. Multimode patterns in image data matrices can vary from nominal to significant due to images with different expressions, pose, illumination, or occlusion variations. We show that manifold learning based image clustering models are unable to achieve well separated images at local level for image datasets with significant multimode data patterns. Because gray level image features used in these clustering models are not able to capture the local neighborhood structure effectively for multimode image datasets. In this study, we use nearest neighborhood quality (NNQ) measure based criterion to improve local neighborhood structure in terms of correct nearest neighbors of images locally. We found Gist as the optimal image descriptor among HOG, Gist, SUN, SURF, and TED image descriptors based on an overall maximum NNQ measure on 10 benchmark image datasets. We observed significant performance improvement for recently reported clustering models such as Spectral Embedded Clustering (SEC) and Nonnegative Spectral Clustering with Discriminative Regularization (NSDR) using proposed approach. Experimentally, significant overall performance improvement of 10.5% (clustering accuracy) and 9.2% (normalized mutual information) on 13 benchmark image datasets is observed for SEC and NSDR clustering models. Further, overall computational cost of SEC model is reduced to 19% and clustering performance for challenging outdoor natural image databases is significantly improved by using proposed NNQ measure based optimal image representations. key words: multimode image clustering, spectral embedded clustering, nonnegative spectral constraint, NNQ measure, Gist image descriptor

show abstract