Security Event Recognition for Visual Surveillance

Liao, Wuping; Chun, Yang; Yang, Michael Ying; Rosenhahn, Bodo

doi:10.5194/isprs-annals-iv-1-w1-19-2017

Cited by 15 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…O BJECT detection is one of the most fundamental and challenging tasks in computer vision, which is widely used in surveillance [1], biomedical analysis [2], digital map construction [3], and autonomous driving [4], [5]. As objects can exist at any positions with different scales in a given image, it is exhaustive to directly search everywhere.…”

Section: Introductionmentioning

confidence: 99%

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

Zou

Zhang

Peng

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Current state-of-the-art two-stage detectors heavily rely on region proposals to guide the accurate detection for objects. In previous region proposal approaches, the interaction between different functional modules is correlated weakly, which limits or decreases the performance of region proposal approaches. In this paper, we propose a novel two-stage strong correlation learning framework, abbreviated as SC-RPN, which aims to set up stronger relationship among different modules in the region proposal task. Firstly, we propose a Light-weight IoU-Mask branch to predict intersection-over-union (IoU) mask and refine region classification scores as well, it is used to prevent high-quality region proposals from being filtered. Furthermore, a sampling strategy named Size-Aware Dynamic Sampling (SADS) is proposed to ensure sampling consistency between different stages. In addition, point-based representation is exploited to generate region proposals with stronger fitting ability. Without bells and whistles, SC-RPN achieves AR1000 14.5% higher than that of Region Proposal Network (RPN), surpassing all the existing region proposal approaches. We also integrate SC-RPN into Fast R-CNN and Faster R-CNN to test its effectiveness on object detection task, the experimental results achieve a gain of 3.2% and 3.8% in terms of mAP compared to the original ones.

show abstract

Section: Introductionmentioning

confidence: 99%

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

Zou

Zhang

Peng

et al. 2021

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Therefore, one can see more use-cases related to object classification (document classification being just a subset). Some well-known real-world examples of such usages are image recognition and detection [3], emotion-sensing from face images, e.g., in the context of driver status monitoring [4], machine vision involving search and rescue missions using drones, performing video-based traffic control and surveillance [5], etc.…”

Section: Introductionmentioning

confidence: 99%

“…Sensors 2021, 21, x FOR PEER REVIEW 2 of 21 search and rescue missions using drones, performing video-based traffic control and surveillance [5], etc. The management of hardcopy documents within an enterprise (a company) traditionally requires too much time and knowledge for the secretarial and archival staff to fully understand the various documents' contents and classify them appropriately.…”

Section: Introductionmentioning

confidence: 99%

A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions

Mohsenzadegan

Tavakkoli

Kyamakya

2021

Sensors

View full text Add to dashboard Cite

This paper’s core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc. Document classification is a special machine vision task in which document images are categorized according to their likelihood. Document classification is by itself an important topic for the digital office and it has several usages. Additionally, different methods for solving this problem have been presented in various studies; their respectively reached performance is however not yet good enough. This task is very tough and challenging. Thus, a novel, more accurate and precise model is needed. Although the related works do reach acceptable accuracy values for less hard conditions, they generally fully fail in the face of those above-mentioned hard, real-world conditions, including, amongst others, distortions such as noise, blur, low contrast, and shadows. In this paper, a novel deep CNN model is developed, validated and benchmarked with a selection of the most relevant recent document classification models. Additionally, the model’s sensitivity was significantly improved by injecting different artifacts during the training process. In the benchmarking, it does clearly outperform all others by at least 4%, thus reaching more than 96% accuracy.

show abstract

“…For security applications, the integration of multisensor information has been recently proposed towards the efficient fusion of the heterogeneous information towards robust large-scale video surveillance system [8]. In particular, multiple target detection, tracking, and security event recognition is an important application of computer vision with significant attention on human motion/activity recognition and abnormal event detection [9]. Most algorithms are based on learning robust background models from standard optical RGB cameras [10][11][12][13][14] and more recently from other infrared sensors and deep learning architectures [15].…”

Section: Introductionmentioning

confidence: 99%

Fusing Multimodal Video Data for Detecting Moving Objects/Targets in Challenging Indoor and Outdoor Scenes

2019

View full text Add to dashboard Cite

Single sensor systems and standard optical—usually RGB CCTV video cameras—fail to provide adequate observations, or the amount of spectral information required to build rich, expressive, discriminative features for object detection and tracking tasks in challenging outdoor and indoor scenes under various environmental/illumination conditions. Towards this direction, we have designed a multisensor system based on thermal, shortwave infrared, and hyperspectral video sensors and propose a processing pipeline able to perform in real-time object detection tasks despite the huge amount of the concurrently acquired video streams. In particular, in order to avoid the computationally intensive coregistration of the hyperspectral data with other imaging modalities, the initially detected targets are projected through a local coordinate system on the hypercube image plane. Regarding the object detection, a detector-agnostic procedure has been developed, integrating both unsupervised (background subtraction) and supervised (deep learning convolutional neural networks) techniques for validation purposes. The detected and verified targets are extracted through the fusion and data association steps based on temporal spectral signatures of both target and background. The quite promising experimental results in challenging indoor and outdoor scenes indicated the robust and efficient performance of the developed methodology under different conditions like fog, smoke, and illumination changes.

show abstract

Security Event Recognition for Visual Surveillance

Cited by 15 publications

References 24 publications

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

SC-RPN: A Strong Correlation Learning Framework for Region Proposal

A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions

Fusing Multimodal Video Data for Detecting Moving Objects/Targets in Challenging Indoor and Outdoor Scenes

Contact Info

Product

Resources

About