Unsupervised Change Detection in Wide-Field Video Images Under Low Illumination

Shi, Baoqiang; Jia, Zhenghong; Yang, Jie; Kasabov, Nikola

doi:10.1109/tcsvt.2022.3216457

Cited by 8 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This test initially assesses the difference feature extraction performance of the newly introduced WeibDO in comparison to several existing operators, including SO [3] , LRO [4] , MRO [5] , NRO [6] , and EPRO [7] . Subsequently, a comprehensive evaluation is conducted to compare the overall performance of the proposed algorithm with other prominent change detection algorithms, including PCAK [8] , CDIK [9] , NR_ELM [10] , CWNN [11] , ASEA [12] , Zhu [13] , NPSG [14] , INLPG [15] and Shi [7] . we calculate evaluation metrics such as overall error (OE), percentage of correct classification (PCC), Kappa coefficient (KC), and F1 score (F1), respectively.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Coarse-to-fine change detection in low-illumination video sequences via classifier trained on ResNet18

Lin,

Jia

2024

International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024)

View full text Add to dashboard Cite

In low-illumination environments, the contrast between targets and the background sharply decreases, and imaging sensors introduce complex random noise while capturing more light, leading to severe distortion in the target features of visible light images. Under these conditions, target feature-based detection algorithms face significant challenges. In this paper, we propose a coarse-to-fine change detection algorithm that detects targets in low-illumination environments by focusing on the change features generated by the targets. First, a binary classifier based on ResNet18 is trained with a specially curated dataset of targets and noise. Second, this classifier is applied to identify potential change objects in test data, preserve targets, and extract corresponding bi-temporal local regions of interest. Third, novel difference feature extraction operators are employed to generate local difference images. Next, a Laplacian-of-Gaussian-based graph cut algorithm is used to perform binary segmentation, distinguishing foreground from background in the images. We validated the feasibility of this algorithm in three challenging night scenes. Compared with the current state-of-the-art unsupervised change detection algorithms, the proposed algorithm shows overall better detection performance.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Subsequently, morphological filtering is performed on the normalized candidates using structuring elements 1 E , 2 E , and 3 E to selectively remove interference features. This is followed by the application of a weighted average for the fusion and amplification of prominent features, as detailed in (7). 1 1…”

Section: Tn-disnetmentioning

confidence: 99%

Coarse-to-fine change detection in low-illumination video sequences via classifier trained on ResNet18

Lin,

Jia

2024

International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024)

View full text Add to dashboard Cite

show abstract

“…There are two parts of the experiment, a subjective analysis and an objective evaluation. The other eight methods are Zhu [8] , IRG_Mcs [9] , AGSCC [10] , FDA_RMG [11] , Shi [12] . The experimental setup encompassed an Intel Core i7-11500H processor operating at a frequency of 3.60GHz, accompanied by 12 GB of memory.…”

Section: Experimental Analysismentioning

confidence: 99%

Unsupervised wide field-of-view video image change detection

liu,

jia,

Huang

et al. 2024

International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024)

View full text Add to dashboard Cite

Video surveillance requires simultaneous monitoring of multiple areas. Consequently, real-time automatic change detection of the monitored areas becomes very important. In the context of wide field-of-view conditions, the combination of a wide field-of-view, intricate environmental factors, and a substantial presence of random noise can lead to the degradation of visual fidelity and a diminished signal-to-noise ratio in the video images acquired through the image sensor. As a consequence, the task of detecting subtle changes becomes challenging for the surveillance system. To address the above problems, we have proposed a change detection method that leverages improved difference images and super fast and robust fuzzy c-means with constraints clustering. Initially, we employ an improved log-ratio operator and an improved mean-ratio operator to generate two distinct difference images. Subsequently, the wavelet fusion algorithm is applied to merge these two difference images, effectively integrating their distinctive features and producing a fused difference image with differentiability. Then, the new difference image is subjected to soft threshold primary classification and a cumulative distribution function normalization to obtain the difference image after primary classification. Finally, the super fast and robust fuzzy c-means with constraints clustering algorithm is employed for the ultimate classification, enabling the separation of changed and unchanged areas within the image.

show abstract

Nighttime large-field video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion

Ren,

He,

Jia

et al. 2024

Displays

View full text Add to dashboard Cite

Unsupervised Change Detection in Wide-Field Video Images Under Low Illumination

Abstract: His research direction is the change detection of the wide-field video images under low illumination.

Cited by 8 publications

References 53 publications

Coarse-to-fine change detection in low-illumination video sequences via classifier trained on ResNet18

Coarse-to-fine change detection in low-illumination video sequences via classifier trained on ResNet18

Unsupervised wide field-of-view video image change detection

Nighttime large-field video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion

Contact Info

Product

Resources

About