Building global image features for scene recognition

Meng, Xiangxu; Wang, Zhengzhi; Wu, Lizhen

doi:10.1016/j.patcog.2011.06.012

Cited by 52 publications

(32 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besides the key-point-based approaches, descriptors using the transformation/inference of whole images [30]- [35] are also popular. Amongst the most similar to our previous contributions [13], [36] is the "fingerprint of a place" [37], [38].…”

Section: A Perception and Descriptorsmentioning

confidence: 99%

Topological Mapping and Scene Recognition With Lightweight Color Descriptors for an Omnidirectional Camera

Liu

Siegwart

2014

IEEE Trans. Robot.

View full text Add to dashboard Cite

Scene recognition problems for mobile robots have been extensively studied. This is important for tasks such as visual topological mapping. Usually, sophisticated key-point-based descriptors are used, which can be computationally expensive. In this paper, we describe a lightweight novel scene recognition method using an adaptive descriptor, which is based on color features and geometric information that are extracted from an uncalibrated omnidirectional camera. The proposed method enables a mobile robot to perform online registration of new scenes onto a topological representation automatically and solve the localization problem to topological regions simultaneously, all in real time. We adopt a Dirichlet process mixture model (DPMM) to describe the online inference process. It is based on an approximation of conditional probabilities of the new measurements given incrementally estimated reference models. It enables online inference speeds of up to 50 Hz for a normal CPU. We compare it with state-of-the-art keypoint descriptors and show the advantage of the proposed algorithm in terms of performance and computational efficiency. A real-world experiment is carried out with a mobile robot equipped with an omnidirectional camera. Finally, we show the results on extended datasets.

show abstract

Section: A Perception and Descriptorsmentioning

confidence: 99%

Topological Mapping and Scene Recognition With Lightweight Color Descriptors for an Omnidirectional Camera

Liu

Siegwart

2014

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…To address these limitations of the BoW method, both bag-of-phrase (BoP) including its extension [5] and fusion of BoW and BoP algorithms [4] have been proposed to increase the descriptive and discriminative power of visual words. The BoP method integrates context information between images and incorporates visual saliency as side information [3][4][5][7][8][9][10]. Visual saliency with high quality segmentation masks [11,12] are also utilized in BoP method to localize region-of-interest (RoI) of images for effective classification.…”

Section: Introductionmentioning

confidence: 99%

Saliency-driven image classification method based on histogram mining and image score

Lei

Tan

Chen

et al. 2015

Pattern Recognition

View full text Add to dashboard Cite

“…bedroom, mountain, or coast) of a single image [1]. Scene recognition is widely used in many aspects, such as robotics path planning, video content analysis, content-based image retrieval, and video surveillance [2].…”

Section: Introductionmentioning

confidence: 99%

“…Bag of visual words (BoW) model [5,6] becomes popular in recent years. BoW model represents an image as an unordered collection of local features, and has demonstrated impressive levels of performance [2]. But the spatial information is neglected in BoW model.…”

Section: Introductionmentioning

confidence: 99%

Combining Local Binary Patterns for Scene Recognition

Song¹,

Guo²

2014

JSW

View full text Add to dashboard Cite

Recently, spatial principal component analysis of census transform histograms (PACT) was proposed to recognize instance and categories of places or scenes in an image. An improved representation called Local Difference Binary Pattern (LDBP) also was proposed and performed better than that of PACT. LDBP is based on the comparisons between center pixel and its neighboring pixels, but the relationship among neighbor pixels is not considered. In this paper, we propose to combine Local Neighbor Binary Pattern (LNBP) with LDBP to construct a spatial representation for scene recognition, because that LNBP can provide complementary information regarding neighboring pixels for LDBP. Experiments on widely used datasets demonstrate that the performance of image recognition is further improved with proposed method. Index Terms-scene recognition, spatial pyramid matching, local binary pattern

show abstract

Building global image features for scene recognition

Cited by 52 publications

References 27 publications

Topological Mapping and Scene Recognition With Lightweight Color Descriptors for an Omnidirectional Camera

Topological Mapping and Scene Recognition With Lightweight Color Descriptors for an Omnidirectional Camera

Saliency-driven image classification method based on histogram mining and image score

Combining Local Binary Patterns for Scene Recognition

Contact Info

Product

Resources

About