Feature-Based Image Patch Classification for Moving Shadow Detection

Russell, Mosin; Zou, Ju Jia; Cai, Weidong

doi:10.1109/tcsvt.2017.2763181

Cited by 26 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SISR has attracted increasing attention in recent years since the quality of reconstructed SR images will seriously affect the accuracy of high-level computer vision tasks such as image classification [51], [52], image segmentation [53], [54], and object detection [55], [56]. In all relevant studies, feature extraction and multi-factor model have attracted our attention.…”

Section: Related Workmentioning

confidence: 99%

Multi-scale Residual Network for Image Super-Resolution

Fang

Mei

et al. 2018

Lecture Notes in Computer Science

671

421

View full text Add to dashboard Cite

Convolutional neural networks have been proven to be of great benefit for single-image super-resolution (SISR). However, previous works do not make full use of multi-scale features and ignore the inter-scale correlation between different upsampling factors, resulting in sub-optimal performance. Instead of blindly increasing the depth of the network, we are committed to mining image features and learning the interscale correlation between different upsampling factors. To achieve this, we propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB). Among them, MDCB aims to detect multi-scale features and maximize the use of image features flow at different scales, HFDB focuses on adaptively recalibrate channel-wise feature responses to achieve feature distillation, and DRB attempts to reconstruct SR images with different upsampling factors in a single model. It is worth noting that all these modules can run independently. It means that these modules can be selectively plugged into any CNN model to improve model performance. Extensive experiments show that MDCN achieves competitive results in SISR, especially in the reconstruction task with multiple upsampling factors. The code will be provided at https://github.com/MIVRC/MDCN-PyTorch.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-scale Residual Network for Image Super-Resolution

Fang

Mei

et al. 2018

Lecture Notes in Computer Science

671

421

View full text Add to dashboard Cite

show abstract

“…The solution to the problem of shadow detection is also mentioned on the agenda [ 13 ]. Due to the shadow of infrared remote sensing images, the inspectors are often in a state of long-term intense work, which not only exacerbates the psychological pressure of the staff, but also increases the difficulty of image discrimination [ 14 ].…”

Section: Research On Shadow Detection Methods Of Infrared Remote Sensimentioning

confidence: 99%

Research on Shadow Detection Method of Infrared Remote Sensing Image Based on Artificial Intelligence

Jia

Wang

2020

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

In the process of the development of science and technology in China, in order to maximize the use of network and high-tech resources, more and more fields are increasingly being used for artificial intelligence during this period to meet the growing demand for high technology and requirements. Artificial intelligence is necessary to detect the shadow of infrared remote sensing images. Therefore, in the field of image detection, artificial intelligence must be applied appropriately. In this paper, through the research on the characteristics of artificial intelligence and the artificial intelligence infrared shadow image detection method, the importance of artificial intelligence for infrared remote sensing image detection is deeply analyzed. The significance of research on infrared remote sensing image shadow detection based on artificial intelligence is emphasized.

show abstract

“…During the past decade, a variety of moving shadow elimination algorithms continually spring up. Usually, these methods are mainly divided into four categories: geometry-based methods [4], [22], texture-based methods [5], [29], [30], chromaticity-based methods [6], [31], and physical model-based methods [7]. Geometry-based methods assume that light source, object shape, and the ground plane are known, using the information of direction, size, and shape of shadows to detect shadows [8].…”

Section: Introductionmentioning

confidence: 99%

A Moving Shadow Elimination Method Based on Fusion of Multi-Feature

Zhang

Li³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Moving shadow elimination plays an important role in the field of moving object detection. However, the accuracy of shadow elimination is an open question, due to illumination and complex texture. Furthermore, the problem of misclassification of moving object caused by shadow has also become increasingly serious. To address this problem, this paper presents a moving shadow elimination algorithm based on the fusion of multi-feature pattern, which can enhance the accuracy of moving object detection system. In this approach, a dual-channel HSV color space feature and a uniform extended scale invariant local ternary pattern (UESILTP) texture feature are synthesized to elimination shadow. It greatly overcomes the misjudgment of dark object by color feature and the false detection caused by inconspicuous texture characteristics of moving object. Meantime, a method of region growth is adopted to fill the existing cavities in the color space. Finally, qualitative and quantitative comparisons with state-of-the-art methods show that the algorithm is effective.

show abstract

Feature-Based Image Patch Classification for Moving Shadow Detection

Cited by 26 publications

References 37 publications

Multi-scale Residual Network for Image Super-Resolution

Multi-scale Residual Network for Image Super-Resolution

Research on Shadow Detection Method of Infrared Remote Sensing Image Based on Artificial Intelligence

A Moving Shadow Elimination Method Based on Fusion of Multi-Feature

Contact Info

Product

Resources

About