An automated video surveillance system using Viewpoint Feature Histogram and CUDA-enabled GPUs

Jha, Saurabh; Trivedi, Priyank

doi:10.1109/icacci.2013.6637456

Cited by 7 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the growing capability of object detectors, modern video storage systems (i.e., automated surveillance system [4,9,17]) can identify the objects in each video frame accurately. Nevertheless, due to the performance mismatch between existing block-based storage systems and CNN-based object detection, the efficiency of storing and indexing video clips with specified object categories after CNN inference is degraded.…”

Section: Observationmentioning

confidence: 99%

A Real-Time Feature Indexing System on Live Video Streams

Chakraborty

Pawar

Jang

et al. 2020

2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)

View full text Add to dashboard Cite

Most of the existing video storage systems rely on offline processing to support the feature-based indexing on video streams. The feature-based indexing technique provides an effective way for users to search video content through visual features, such as object categories (e.g., cars and persons). However, due to the reliance on offline processing, video streams along with their captured features cannot be searchable immediately after video streams are recorded. According to our investigation, buffering and storing live video steams are more time-consuming than the YOLO v3 object detector. Such observation motivates us to propose a real-time feature indexing (RTFI) system to enable instantaneous feature-based indexing on live video streams after video streams are captured and processed through object detectors. RTFI achieves its real-time goal via incorporating the novel design of metadata structure and data placement, the capability of modern object detector (i.e., YOLO v3), and the deduplication techniques to avoid storing repetitive video content. Notably, RTFI is the first system design for realizing real-time feature-based indexing on live video streams. RTFI is implemented on a Linux server and can improve the system throughput by upto 10.60x, compared with the base system without the proposed design. In addition, RTFI is able to make the video content searchable within 20 milliseconds for 10 live video streams after the video content is received by the proposed system, excluding the network transfer latency.

show abstract

Section: Observationmentioning

confidence: 99%

A Real-Time Feature Indexing System on Live Video Streams

Chakraborty

Pawar

Jang

et al. 2020

2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)

View full text Add to dashboard Cite

show abstract

“…Viewpoint Feature Histograms (VFH) descriptor is derived from FPFH and is mainly used in 3D object recognition and classification [16]. The VFH adds a viewpoint variance while retaining its invariance to scale, as shown in Figure 2 [20]. Thus VFH descriptor consists of two parts: a viewpoint direction component and surface shape component comprised of an extended FPFH [16].…”

Section: Description Of 3d Point Featuresmentioning

confidence: 99%

“…The two experiments showed that the VFH outperformed other 3D Shape Descriptors when used alone. Because VFH has high recognition performance and fast computational properties, it has been widely used for objects recognition and classification [16,[19][20][21]. In this paper, the VFH of the point cloud data affiliated with waveform features was calculated and employed for concealed cars extraction.…”

Section: Introductionmentioning

confidence: 99%

A Concealed Car Extraction Method Based on Full-Waveform LiDAR Data

Zhou

Liu

et al. 2016

Mobile Information Systems

View full text Add to dashboard Cite

Concealed cars extraction from point clouds data acquired by airborne laser scanning has gained its popularity in recent years. However, due to the occlusion effect, the number of laser points for concealed cars under trees is not enough. Thus, the concealed cars extraction is difficult and unreliable. In this paper, 3D point cloud segmentation and classification approach based on full-waveform LiDAR was presented. This approach first employed the autocorrelationGcoefficient and the echo ratio to determine concealed cars areas. Then the points in the concealed cars areas were segmented with regard to elevation distribution of concealed cars. Based on the previous steps, a strategy integrating backscattered waveform features and the view histogram descriptor was developed to train sample data of concealed cars and generate the feature pattern. Finally concealed cars were classified by pattern matching. The approach was validated by full-waveform LiDAR data and experimental results demonstrated that the presented approach can extract concealed cars with accuracy more than 78.6% in the experiment areas.

show abstract

“…Entre las plataformas paralelas existentes destaca la Arquitectura Unificada de Dispositivos de Cómputo (CUDA) (Saxena, Sharma and Sharma, 2014), (Vokorokos et al, 2014), la cual permite acelerar aplicaciones de cómputo, aprovechando el poder de las GPU´s (NVIDIA, no date). Recientemente se ha incrementado el uso de la plataforma CUDA (Pawar, 2017), Sin embargo, solo se detallan revisiones del estado del arte llevadas a cabo para acelerar la velocidad de procesamiento digital de imágenes (PDI) en ciertas aplicaciones como la médica (Weinlich et al, 2013) (Jiansen Li et al, 2014) (Lee et al, 2013) y no cubre las diferentes aplicaciones de procesamiento de video utilizando GPU en video vigilancia (Jha and Trivedi, 2013), (Devani, Nikam and Meshram, 2015), (Deligiannidis and Arabnia, 2014), procesamiento de imágenes de Radar de Apertura Sintética (SAR) (Fatica and Phillips, 2014), mejora de súper resolución de imágenes (Feng, Zhang and Gao, 2015), reconocimiento de objetos utilizando descriptor de Fourier (Haythem et al, 2014), criptografía, seguimiento de objetos, reducción de ruido (Yazdanpanah et al, 2014), reconstrucción de imágenes (Zhu et al, 2013) (Kau and Chen, 2013) (Heidari, 2013), detección de rostros (Sun et al, 2013), modelos de actuadores planares (Xu, Dinavahi and Xu, 2016), etc.…”

Section: Introductionunclassified

Utilización de GPU-CUDA en el Procesamiento Digital de Imágenes

Aguilera

Aceves

Argüelles

et al. 2018

CULCyT

View full text Add to dashboard Cite

RESUMENEL procesamiento de imágenes es una herramienta de gran utilidad en diversas aplicaciones como video vigilancia, reconstrucción de imágenes, información geográfica y médica. Sin embargo, estas aplicaciones requieren una gran demanda computacional para ser llevadas a cabo en el menor tiempo posible, aún y que se desarrollan nuevos algoritmos, suelen ser restrictivos para implementarse en tiempo real en sistemas que solo se basan en CPU. Afortunadamente, estos algoritmos pueden ser analizados para llevarse a cabo en plataformas de cómputo paralelo, como las GPU-CUDA. En este trabajo se analizan diferentes revistas de la IEEE desde el 2013, donde se paralelizaron algoritmos con estas aplicaciones y se implementaron con ayuda de GPU´s. Se destaca que el uso de esta herramienta ha ido en crecimiento en el ámbito científico, en diferentes ramas de la ciencia.

show abstract

An automated video surveillance system using Viewpoint Feature Histogram and CUDA-enabled GPUs

Cited by 7 publications

References 6 publications

A Real-Time Feature Indexing System on Live Video Streams

A Real-Time Feature Indexing System on Live Video Streams

A Concealed Car Extraction Method Based on Full-Waveform LiDAR Data

Utilización de GPU-CUDA en el Procesamiento Digital de Imágenes

Contact Info

Product

Resources

About