Scene Recognition through Visual Attention and Image Features: A Comparison between SIFT and SURF Approaches

López-García, Fernando; Fdez-Vidal, Xosé R.; Pardo, Xosé M.; Dosil, Raquel

doi:10.5772/14343

Cited by 13 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The improvement achieved by our model with respect to very recent approaches such as AWS-D [103], DCL [2], WMAP [96] or ICL-D [88] is statistically significant. Moreover, it is also visually noticeable in some intricate cases, as those shown in Figure 4.8, with scenes showing crowds, multiple similar concepts that hamper visual guidance or quick actions.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 63%

“…• López-García et al, 2011 [96]: The authors proposed the Weighted Maximum Phase Alignment (WMAP) measure as a spatial visual attention estimator with the purpose of significantly accelerating a scene recognition task, preserving its performance. The approach considers both efficient coding, in order to reduce the redundancy of the input data, and the detection of important attributes of the image via local edge phase and energy.…”

Section: Bottom-up Versus Top-down Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Topic Model for Context-Driven Visual Attention Understanding

Fernández‐Torres

González-Díaz

Díaz-de-María

2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 63%

Section: Bottom-up Versus Top-down Approachesmentioning

confidence: 99%

Probabilistic Topic Model for Context-Driven Visual Attention Understanding

Fernández‐Torres

González-Díaz

Díaz-de-María

2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Understanding a scene and focusing on its most salient object is the most significant ability of the human visual system [5]. Most of the salient regions are selected from a scene using visual attention, eliminating inadequate information and thus grabbing the useful information from the salient region [6]. It has been found that the movements of the eye and shifting of the attention commences towards the highest salience region and then pauses so that the attention can shift towards the next highest salience region [7].…”

Section: Introductionmentioning

confidence: 99%

The Effect of Eye Movements in Response to Different Types of Scenes Using a Graph-Based Visual Saliency Algorithm

et al. 2019

View full text Add to dashboard Cite

Saliency is the quality of an object that makes it stands out from neighbouring items and grabs viewer attention. Regarding image processing, it refers to the pixel or group of pixels that stand out in an image or a video clip and capture the attention of the viewer. Our eye movements are usually guided by saliency while inspecting a scene. Rapid detection of emotive stimuli an ability possessed by humans. Visual objects in a scene are also emotionally salient. As different images and clips can elicit different emotional responses in a viewer such as happiness or sadness, there is a need to measure these emotions along with visual saliency. This study was conducted to determine whether the existing available visual saliency models can also measure emotional saliency. A classical Graph-Based Visual Saliency (GBVS) model is used in the study. Results show that there is low saliency or salient features in sad movies with at least a significant difference of 0.05 between happy and sad videos as well as a large mean difference of 76.57 and 57.0, hence making these videos less emotionally salient. However, overall visual content does not capture emotional salience. The applied Graph-Based Visual Saliency model notably identified happy emotions but could not analyze sad emotions.

show abstract

“…The visual attention approach is the process that allows machine vision systems to detect the most essential and informative regions in the image. Among the various algorithms computing spatial saliency in images, the Weighted Maximum Phase Alignment (WMAP) model [42] offered appropriate results on various datasets [43]. This model uses the local phase (energy) information of the input data to achieve the saliency map by the integration of the WMAP measures for each pixel of each color channel (c) as follows:…”

mentioning

confidence: 99%

Using Information Content to Select Keypoints for UAV Image Matching

Mousavi¹,

Varshosaz²,

Remondino³

2021

Remote Sensing

View full text Add to dashboard Cite

Image matching is one of the most important tasks in Unmanned Arial Vehicles (UAV) photogrammetry applications. The number and distribution of extracted keypoints play an essential role in the reliability and accuracy of image matching and orientation results. Conventional detectors generally produce too many redundant keypoints. In this paper, we study the effect of applying various information content criteria to keypoint selection tasks. For this reason, the quality measures of entropy, spatial saliency and texture coefficient are used to select keypoints extracted using SIFT, SURF, MSER and BRISK operators. Experiments are conducted using several synthetic and real UAV image pairs. Results show that the keypoint selection methods perform differently based on the applied detector and scene type, but in most cases, the precision of the matching results is improved by an average of 15%. In general, it can be said that applying proper keypoint selection techniques can improve the accuracy and efficiency of UAV image matching and orientation results. In addition to the evaluation, a new hybrid keypoint selection is proposed that combines all of the information content criteria discussed in this paper. This new screening method was also compared with those of SIFT, which showed 22% to 40% improvement for the bundle adjustment of UAV images.

show abstract

Scene Recognition through Visual Attention and Image Features: A Comparison between SIFT and SURF Approaches

Cited by 13 publications

References 19 publications

Probabilistic Topic Model for Context-Driven Visual Attention Understanding

Probabilistic Topic Model for Context-Driven Visual Attention Understanding

The Effect of Eye Movements in Response to Different Types of Scenes Using a Graph-Based Visual Saliency Algorithm

Using Information Content to Select Keypoints for UAV Image Matching

Contact Info

Product

Resources

About