Moving Object Detection With Deep CNNs

Zhu, Haidi; Yan, Xin; Tang, Hongying; Chang, Yuchao; Li, Baoqing; Yuan, Xiaobing

doi:10.1109/access.2020.2972562

Cited by 38 publications

(26 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the use of parallel computing in these processes can greatly reduce the computation cost. Recently, deep learning has been widely used in the field of image processing, such as depth prediction [42], moving object detection [43], and image inpainting [44]. This can provide some help for DIBR-based methods.…”

Section: G Discussionmentioning

confidence: 99%

Local Foreground Removal Disocclusion Filling Method for View Synthesis

Liang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

View synthesis is an effective method to generate the contents of multiple views based on a limited number of reference views, which can be used in 2D to 3D conversion, free viewpoint video and multiview video rendering. Depth-image-based rendering (DIBR) is a practical technique to generate virtual view by using a 2D reference view and its depth image. However, a critical problem in DIBR process is that disocclusions might be produced in the synthesized image because the background occluded by the foreground objects in the reference view may be exposed in the virtual view. In this paper, a local foreground removal method is proposed for disocclusion filling. Morphology-based depth image preprocessing is performed before DIBR, aiming to correct the depth value of the ghosts and remove ghost artifacts. In the synthesized virtual image, pixels on the disocclusion edge are identified and classified. Then they are positioned in the reference image by inverse 3D warping. Local foreground regions that occlude the corresponding background are removed from both the reference image and its depth image based on the disocclusion edge pixels. Removed region is filled with surrounding background contents, and depth information is used in this process to prevent foreground penetration. The predicted background contents are warped to the disocclusion region, thereby achieving the hole filling. Experimental results show that the proposed method performs better than the other methods in disocclusion filling, and improves the subjective and objective quality of the synthesized view. In the evaluation results of PSNR, SSIM, FSIMc and VSI, our method improves by 0.

show abstract

Section: G Discussionmentioning

confidence: 99%

Local Foreground Removal Disocclusion Filling Method for View Synthesis

Liang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Moreover, these methods have difficulty in merging noise-broken objects. To address this issue, in [ 31 ], we presented an efficient algorithm to detect connected regions and merge broken objects at the same time with low computational complexity.…”

Section: Related Workmentioning

confidence: 99%

“…One-stage detectors [ 21 , 38 , 39 , 40 , 41 , 42 ] are introduced to gain computational efficiency. However, for moving object detection that involves high-resolution images, convolutional neural networks face several limitations [ 31 ], including (i) the inability to recognize motion and (ii) the generally much smaller input relative to high-resolution images of the size 1920 × 1080. We proposed the coarse-to-fine grained framework in [ 31 ] to address these issues.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, in this paper, the objective is to achieve real-time detection together with high accuracy. First, the framework in [ 31 ] is used as the starting point. In the coarse-grained detection stage, a more efficient method is considered to obtain moving regions.…”

Section: Related Workmentioning

confidence: 99%

“…Let us begin with the coarse-grained detection block or stage, which consists of moving object detection with downsampling together with low-pass filtering and morphology filtering (opening operation). Then, adjustments are made to the framework in [ 31 ] to obtain connected region detection by mapping the coordinates of moving regions to the original image. In addition, in order to obtain more complete moving regions, the regions are extended.…”

Section: Improved Moving Object Detection Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Moving Object Detection in High-Resolution Video Sensing

Zhu

Wei

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

This paper addresses real-time moving object detection with high accuracy in high-resolution video frames. A previously developed framework for moving object detection is modified to enable real-time processing of high-resolution images. First, a computationally efficient method is employed, which detects moving regions on a resized image while maintaining moving regions on the original image with mapping coordinates. Second, a light backbone deep neural network in place of a more complex one is utilized. Third, the focal loss function is employed to alleviate the imbalance between positive and negative samples. The results of the extensive experimentations conducted indicate that the modified framework developed in this paper achieves a processing rate of 21 frames per second with 86.15% accuracy on the dataset SimitMovingDataset, which contains high-resolution images of the size 1920 × 1080.

show abstract

Detection algorithm of safety helmet wearing based on deep learning

Huang

et al. 2021

Concurrency and Computation

137

View full text Add to dashboard Cite

In the production and construction of industry, safety accidents caused by unsafe behaviors of staff often occur. In a complex construction site scene, due to improper operations by personnel, huge safety risks will be buried in the entire production process. The use of deep learning algorithms to replace manual monitoring of site safety regulations is a powerful guarantee for sticking to the line of safety in production. First, the improved YOLO v3 algorithm is used to output the predicted anchor box of the target object, and then pixel feature statistics are performed on the anchor box, and the weight coefficients are respectively multiplied to output the confidence of the standard wearing of the helmet in each predicted anchor box area, according to the empirical threshold determine whether workers meet the standards for wearing helmets. Experimental results show that the helmet wearing detection algorithm based on deep learning in this paper increases the feature map scale, optimizes the prior dimensional algorithm of specific helmet dataset, and improves the loss function, and then combines image processing pixel feature statistics to accurately detect whether the helmet is worn by the standard. The final result is that mAP reaches 93.1% and FPS reaches 55 f/s. In the helmet recognition task, compared to the original YOLO v3 algorithm, mAP is increased by 3.5% and FPS is increased by 3 f/s. It shows that the improved detection algorithm has a better effect on the detection speed and accuracy of the helmet detection task.

show abstract

Moving Object Detection With Deep CNNs

Cited by 38 publications

References 36 publications

Local Foreground Removal Disocclusion Filling Method for View Synthesis

Local Foreground Removal Disocclusion Filling Method for View Synthesis

Real-Time Moving Object Detection in High-Resolution Video Sensing

Detection algorithm of safety helmet wearing based on deep learning

Contact Info

Product

Resources

About