Video Anomaly Detection using Pre-Trained Deep Convolutional Neural Nets and Context Mining

Wu, Chongke; Shao, Sicong; Tunc, Cihan; Hariri, Salim

doi:10.1109/aiccsa50499.2020.9316538

Cited by 23 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computational complexity of the known neural network models [11][12][13][14][15][16][17][18] is one of their disadvantages. A solution to this problem can be found in the use of direct (Kronecker) penetrating product of matrices for the analytical description of operations performed in a concrete DCNN layer (expressions ( 10)-( 24)).…”

Section: Discussion Of the Results Obtained In The Study Of Recognizing The Object Images In Aerial Photographs Using Dcnnmentioning

confidence: 99%

See 1 more Smart Citation

Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

Slyusar

Protsenko

Chernukha

et al. 2021

EEJET

View full text Add to dashboard Cite

Detection and recognition of objects in images is the main problem to be solved by computer vision systems. As part of solving this problem, the model of object recognition in aerial photographs taken from unmanned aerial vehicles has been improved. A study of object recognition in aerial photographs using deep convolutional neural networks has been carried out. Analysis of possible implementations showed that the AlexNet 2012 model (Canada) trained on the ImageNet image set (China) is most suitable for this problem solution. This model was used as a basic one. The object recognition error for this model with the use of the ImageNet test set of images amounted to 15 %. To solve the problem of improving the effectiveness of object recognition in aerial photographs for 10 classes of images, the final fully connected layer was modified by rejection from 1,000 to 10 neurons and additional two-stage training of the resulting model. Additional training was carried out with a set of images prepared from aerial photographs at stage 1 and with a set of VisDrone 2021 (China) images at stage 2. Optimal training parameters were selected: speed (step) (0.0001), number of epochs (100). As a result, a new model under the proposed name of AlexVisDrone was obtained. The effectiveness of the proposed model was checked with a test set of 100 images for each class (the total number of classes was 10). Accuracy and sensitivity were chosen as the main indicators of the model effectiveness. As a result, an increase in recognition accuracy from 7 % (for images from aerial photographs) to 9 % (for the VisDrone 2021 set) was obtained which has indicated that the choice of neural network architecture and training parameters was correct. The use of the proposed model makes it possible to automate the process of object recognition in aerial photographs. In the future, it is advisable to use this model at ground stations of unmanned aerial vehicle complex control when processing aerial photographs taken from unmanned aerial vehicles, in robotic systems, in video surveillance complexes and when designing unmanned vehicle systems

show abstract

Section: Discussion Of the Results Obtained In The Study Of Recognizing The Object Images In Aerial Photographs Using Dcnnmentioning

confidence: 99%

“…Anomaly detection [16] is critically important for intelligent surveillance systems. Many approaches to detecting video anomalies using deep training techniques focus on video streams from individual cameras.…”

Section: Detection and Recognition Of Objects In Images Is The Main Problem To Be Solved By Computer Vision Systems As Part Of Solving Thmentioning

confidence: 99%

Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

Slyusar

Protsenko

Chernukha

et al. 2021

EEJET

View full text Add to dashboard Cite

show abstract

“…Anomaly detection in crowded scenes has been addressed in numerous ways using a variety of algorithms including classical machine learning schemes, for example, k-means and SVMs (Yang et al 2019), GMM, and so forth, as well as deep learning methods, for example, CNNs (Joshi and Patel 2021;Pang et al 2020;Wu et al 2020), LSTM (Esan, Owolawi, and Tu 2020), GANs (Luo, Liu, and Gao 2017a;Chen et al 2021), and autoencoders (AEs) (Simonyan and Zisserman 2014;Pawar and Attar 2021), bag-of-words (BOW) method, and physics-inspired approaches (Wu, Moore, and Shah 2010), and so forth. These methods are often inter-related and the exact taxonomy is difficult.…”

Section: Methods and State-of-the-artmentioning

confidence: 99%

Visual crowd analysis: Open research problems

Khan,

Menouar,

Hamila

2023

AI Magazine

View full text Add to dashboard Cite

Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep‐learning approaches have made it possible to develop fully automated vision‐based crowd‐monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state‐of‐the‐art.

show abstract

“…We also suggest improving the adapted MMA algorithm by adding a frame differencing method as a pre-processing step, then exploiting better multi-scale feature selection to improve average F-score with reference to some of the latest models [35]- [44] on object detection and their post-processing schemes [45]. Furthermore, we are investigating some of the recent deep learning schemes [46]- [57] for detecting and tracking vehicles [27], [34], [39], [58]- [61] in accordance with the complexity analysis [45], [62]- [69] from the deep CNN-based multi-object detection and segmentation schemes [48]- [51], [53]- [56], [59]- [61], [64]- [66], [70]- [72] applied to wide-area aerial surveillance.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Spatio-Temporal Processing for Automatic Vehicle Detection in Wide-Area Aerial Video

et al. 2020

Self Cite

View full text Add to dashboard Cite

Vehicle detection in aerial videos often requires post-processing to eliminate false detections. This paper presents a spatio-temporal processing scheme to improve automatic vehicle detection performance by replacing the thresholding step of existing detection algorithms with multi-neighborhood hysteresis thresholding for foreground pixel classification. The proposed scheme also performs spatial post-processing, which includes morphological opening and closing to shape and prune the detected objects, and temporal post-processing to further reduce false detections. We evaluate the performance of the proposed spatial processing on two local aerial video datasets and one parking vehicle dataset, and the performance of the proposed spatio-temporal processing scheme on five local aerial video datasets and one public dataset. Experimental evaluation shows that the proposed schemes improve vehicle detection performance for each of the nine algorithms when evaluated on seven datasets. Overall, the use of the proposed spatio-temporal processing scheme improves average F-score to above 0.8, achieves a 90% reduction in false positives and reduces percentage of wrong classifications to below 50% for some of the nine algorithms. INDEX TERMS Vehicle detection, hysteresis thresholding, spatio-temporal processing, wide-area aerial imagery.

show abstract

Video Anomaly Detection using Pre-Trained Deep Convolutional Neural Nets and Context Mining

Cited by 23 publications

References 35 publications

Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

Improvement of the model of object recognition in aero photographs using deep convolutional neural networks

Visual crowd analysis: Open research problems

Spatio-Temporal Processing for Automatic Vehicle Detection in Wide-Area Aerial Video

Contact Info

Product

Resources

About