Learning a Sparse Representation for Object Detection

Agarwal, Shivani; Roth, Dan

doi:10.1007/3-540-47979-1_8

Cited by 359 publications

(371 citation statements)

References 9 publications

Supporting

Mentioning

371

Contrasting

Order By: Relevance

“…For human detection, we trained a 128 × 64 model using INRIA person dataset as described in [7]. For car detection, we trained a 40 × 100 model using UIUC [1] and Darmstadt [15] sets together totalling 602 car side views. The model trained for van detection is 40 × 100 as well.…”

Section: Methodsmentioning

confidence: 99%

“…Table 1 summarizes the result of the comparison, where we see that the mean score (also minimum, maximum and quartiles) for the proposed approach is higher than that of regular HOG window. For synthetic car images, 602 perspective car images from UIUC [1] and Darmstadt [15] datasets are projected to omnidirectional images. 40×100 pixel regular HOG computation and the proposed non-rectangular HOG window are compared in Table 2.…”

Section: Evaluation Of the Proposed Hog Computation Using Synthetic Omentioning

confidence: 99%

“…A second contribution is that we construct an omnidirectional image dataset with annotated humans, cars and vans and it can be downloaded from our website 1 . We believe this dataset will be useful to the community for omnidirectional vision-based object detection research.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A direct approach for object detection with catadioptric omnidirectional cameras

Cinaroglu

Baştanlar

2015

SIViP

View full text Add to dashboard Cite

In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred. Keywords Catadioptric omnidirectional cameras · Object detection · Human detection · Car detection · Vehicle detectionElectronic supplementary material The online version of this article

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Evaluation Of the Proposed Hog Computation Using Synthetic Omentioning

confidence: 99%

See 1 more Smart Citation

A direct approach for object detection with catadioptric omnidirectional cameras

Cinaroglu

Baştanlar

2015

SIViP

View full text Add to dashboard Cite

show abstract

“…This parallel has been exploited in recent bag-of-keypoints approaches to visual categorization [6,27], unsupervised discovery of visual "topics" [24], and video retrieval [23]. More generally, representations based on local image features, or salient regions extracted by specialized interest operators, have shown promise for recognizing textures [13], different views of the same object [9,22], and different instances of the same object class [1,7,8,26]. For textures, appearance-based descriptors of salient local regions are clustered to form characteristic texture elements, or textons.…”

Section: Introductionmentioning

confidence: 99%

A Discriminative Framework for Texture and Object Recognition Using Local Image Features

Lazebnik

Schmid

Ponce

2006

Toward Category-Level Object Recognition

View full text Add to dashboard Cite

Abstract. This chapter presents an approach for texture and object recognition that uses scale-or affine-invariant local image features in combination with a discriminative classifier. Textures are represented using a visual dictionary found by quantizing appearance-based descriptors of local features. Object classes are represented using a dictionary of composite semi-local parts, or groups of nearby features with stable and distinctive appearance and geometric layout. A discriminative maximum entropy framework is used to learn the posterior distribution of the class label given the occurrences of parts from the dictionary in the training set. Experiments on two texture and two object databases demonstrate the effectiveness of this framework for visual classification.

show abstract

“…In contrast, object recognition based on dense local "invariant" image features have shown a lot of success recently [8,11,14,19,1,3,6,16,7] for objects with large withinclass variability in shape and appearance. In such approaches objects are modeled as a collection of parts or local features and the recognition is based on inferring object class based on similarity in parts' appearance and their spatial arrangement.…”

Section: Introductionmentioning

confidence: 99%

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Zhao

Elgammal

2006

Advances in Machine Vision, Image Processing, and Pattern Analysis

View full text Add to dashboard Cite

Abstract. In an object recognition task where an image is represented as a constellation of image patches, often many patches correspond to the cluttered background. If such patches are used for object class recognition, they will adversely affect the recognition rate. In this paper, we present a statistical method for selecting the image patches which characterize the target object class and are capable of discriminating between the positive images containing the target objects and the complementary negative images. This statistical method select those images patches from the positive images which, when used individually, have the power of discriminating between the positive and negative images in the evaluation data. Another contribution of this paper is the part-based probabilistic method for object recognition. This Bayesian approach uses a common reference frame instead of reference patch to avoid the possible occlusion problem. We also explore different feature representation using PCA an 2D PCA. The experiment demonstrates our approach has outperformed most of the other known methods on a popular benchmark data set while approaching the best known results.

show abstract

Learning a Sparse Representation for Object Detection

Cited by 359 publications

References 9 publications

A direct approach for object detection with catadioptric omnidirectional cameras

A direct approach for object detection with catadioptric omnidirectional cameras

A Discriminative Framework for Texture and Object Recognition Using Local Image Features

A Statistically Selected Part-Based Probabilistic Model for Object Recognition

Contact Info

Product

Resources

About