Event detection for intelligent car park video surveillance

Diamantopoulos, Georgios; Spann, Michael

doi:10.1016/j.rti.2005.02.002

Cited by 16 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Behavior detection and event recognition are also crucial in this regard to detect intrusion [31] and movement disorder [32]. Learning and classification are other powerful ways for object detection and event recognition [33]. Bio-inspired adaptive hyperspectral imaging for real-time target tracking [34] and a brain-inspired neural-cognitive approach for thermal image analysis [35] are some examples.…”

Section: Vss Requirementsmentioning

confidence: 99%

Choice of Application Layer Protocols for Next Generation Video Surveillance Using Internet of Video Things

Sultana

Wahid

2019

IEEE Access

View full text Add to dashboard Cite

Video surveillance has become ubiquitous due to the increasing security requirements in every sphere of life. The next generation video surveillance system (VSS) possesses great challenges in various applications, such as intelligent urban surveillance systems and smart cities. In these applications, we need to deal with the fast-growing number of surveillance nodes which introduce several constraints, e.g., high latency, high bandwidth, high energy consumption, and CPU and memory usage. To address these issues, the Internet of Video Things (IoVT), which is considered to be a part of the Internet of Things (IoT), can be a solution. The IoVT is composed of visual sensors (i.e., cameras) connected to the Internet. Unlike conventional systems, the VSS under an IoVT framework provides multiple layers (i.e., edge, fog, and cloud) of communication and decision making by capturing and analyzing rich contextual and behavioral information. Since an appropriate application layer protocol (ALP) can help in alleviating the challenges of future VSSs, the selection of ALPs is important for IoVT-based systems. Therefore, this paper presents a generic architecture of an IoVT-based VSS and a comparative analysis of several ALPs, such as MQTT, AMQP, HTTP, XMPP, CoAP, and DDS, with real-time experimentation. This analysis will assist the users to choose the appropriate ALPs in various surveillance applications and determine their suitability at different nodes of the IoVT framework.INDEX TERMS Application layer protocols, the Internet of Video Things (IoVT), video analytics, video surveillance.

show abstract

Section: Vss Requirementsmentioning

confidence: 99%

Choice of Application Layer Protocols for Next Generation Video Surveillance Using Internet of Video Things

Sultana

Wahid

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…There are usually two types of widely used features: 1) highlevel features abstracted from the detected objects by tracking and recognizing process; 2) low-level features directly derived from the image pixels. Most commonly used object-based 5 features are the position and trajectory of the object's centroid, which have been proved to be effective in detection of various types of anomalies, such as running and falling [28] and traffic anomaly [29]. In addition, features such as limb angles [30] [31] can be used to identify the poses or actions performed by the objects when the resolution of the videos is high enough.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised discovery of crowd activities by saliency-based clustering

et al. 2016

View full text Add to dashboard Cite

“…Video analytics in surveillance has historically relied heavily on cloud-based solutions, which, while effective, pose significant difficulties. [7]; These difficulties include issues with data privacy and security, high bandwidth consumption, and latency in data transmission. In response to these limitations, a revolutionary shift in the surveillance industry is in progress, as evidenced by the growing use of Edge AI, in which artificial intelligence algorithms are built right into edge devices like cameras and network video recorders.…”

Section: Introductionmentioning

confidence: 99%

Edge AI for Real-Time Video Analytics in Surveillance Systems

K P N V Satyasree

2023

IJRITCC

View full text Add to dashboard Cite

More and more surveillance systems are being used to increase security and safety for the general public. However, the conventional method of processing all video data in the cloud can be ineffective and slow response times. By performing video analytics at the network's edge, close to where the data is created, Edge AI is a promising new strategy that can address these issues. The most recent developments in edge AI for real-time video analytics in security systems are discussed in this paper. We discuss the different techniques that are being used, as well as the applications that are being enabled by edge AI. The paper also discusses the challenges and limitations of edge AI, and the future research directions in this area.

show abstract

Event detection for intelligent car park video surveillance

Cited by 16 publications

References 15 publications

Choice of Application Layer Protocols for Next Generation Video Surveillance Using Internet of Video Things

Choice of Application Layer Protocols for Next Generation Video Surveillance Using Internet of Video Things

Unsupervised discovery of crowd activities by saliency-based clustering

Edge AI for Real-Time Video Analytics in Surveillance Systems

Contact Info

Product

Resources

About