Change Detection in Multitemporal Monitoring Images Under Low Illumination

Abstract

Video surveillance may involve the simultaneous monitoring of a large number of areas. Realtime automatic change detection of a monitoring area (such as involving the movement of people or vehicles) can reduce risks incurred in negligent manual observation. However, the low signal-to-noise ratio (SNR) of dark environments can significantly corrupt camera images, making it difficult for machine learning surveillance systems to detect small changes in monitored images. In addition, in the absence of changes between two multitemporal monitoring images, sensor noise can lead to false alarms. The objective of this paper is to reduce the effect of sensor noise on change detection of monitored images and the run time of change detection algorithms. For these purposes, we proposed a novel multitemporal monitoring image change detection algorithm based on morphological structure filtering and normalized fusion difference image. First, the random noise in two surveillance images was removed using a multidirectional weighted multiscale series of a morphological filter. Next, two difference images were obtained by using the compression log-ratio operator and the mean ratio operator, and a fusion difference image was obtained by equal-weight fusion of the two difference images. Then, the sigmoid function was used to compress the fusion difference map to obtain a normalized fusion difference image, and a median filter was used to obtain a final difference image. Finally, the k-means clustering algorithm was utilized to obtain the change detection results. The experimental results demonstrate that the proposed method can accurately detect changes in a night monitoring scene in real time. Subjective and objective evaluation of the experimental results demonstrate that the proposed method is superior to reference algorithms in terms of change detection accuracy, time and robustness. INDEX TERMS change detection; morphological structure filtering; normalized fusion difference map; low illumination monitoring image

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

“…For image CD, the quality of the DI determines the CD performance. Common methods for generating DI mainly include the subtraction operator [17] and log-ratio operator [12], but it is difficult to obtain more details of the changed regions by using a single method to generate DI. Therefore, some scholars are exploring how to obtain high-quality DI.…”

“…Therefore, the fusion of the DIs obtained by the log-ratio operator and the extremum pixel ratio operator can effectively reduce noise interference. Inspired by equal-weight fusion method adopted by Zhu et al [12], we combine the energy of the DI and the Laplacian pyramid to extract more detailed information at multiple scales for achieving a better fusion effect. The fused DI can be obtained by Eq.…”

“…Although most noise in the image is effectively suppressed by filtering, there is still a small amount of noise that will lead to false alarms in the surveillance system. Inspired by reference [12], we compress the fused DI to between [0,1] by a normalization function, which is mainly to suppress the random noise caused by sensors and improve the performance of subsequent clustering. As shown in Fig.…”

“…However, in a low illumination environment, the imaging process is polluted by various mixed noises, such as speckle noise and dark current noise, whose removal requires special means. For example, Zhu et al [12] used a morphological structure filter to effectively remove random noise from video images under low illumination conditions, thereby improving the accuracy of CD.…”

Object Recognition at Night Scene Based on DCGAN and Faster R-CNN

“…Z. Li et al [12] used HSV color space features instead of the traditional RGB space to enhance the robustness of video contrast and color distortion. Y. Zhu et al [13] proposed a novel multitemporal monitoring image change detection algorithm under low-illuminance by fusing different images to remove noise, and achieved good experimental results. The dimness of light is usually the key factor that affects our judgment of foreground objects.…”