A flexible architecture for H.263 video coding

Garrido, M.J.; Sanz, C.; Jimenez, M.; Meneses, Juan

doi:10.1016/s1383-7621(03)00094-8

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPS readings were recorded in conjunction with the video at 1 Hz. The full-HD recordings [ 33 , 34 ] have been time-synchronized such that the position of the train in an arbitrary frame from one video corresponds to the same frame in any of the other three videos. This was achieved by using the recorded GPS positions through interpolation of the GPS measurements to 25 Hz to match the video frame rate.…”

Section: Methodsmentioning

confidence: 99%

Visual Localization across Seasons Using Sequence Matching Based on Multi-Feature Combination

Qiao

Cappelle

Ruichek

2017

Sensors

View full text Add to dashboard Cite

Visual localization is widely used in autonomous navigation system and Advanced Driver Assistance Systems (ADAS). However, visual-based localization in seasonal changing situations is one of the most challenging topics in computer vision and the intelligent vehicle community. The difficulty of this task is related to the strong appearance changes that occur in scenes due to weather or season changes. In this paper, a place recognition based visual localization method is proposed, which realizes the localization by identifying previously visited places using the sequence matching method. It operates by matching query image sequences to an image database acquired previously (video acquired during traveling period). In this method, in order to improve matching accuracy, multi-feature is constructed by combining a global GIST descriptor and local binary feature CSLBP (Center-symmetric local binary patterns) to represent image sequence. Then, similarity measurement according to Chi-square distance is used for effective sequences matching. For experimental evaluation, the relationship between image sequence length and sequences matching performance is studied. To show its effectiveness, the proposed method is tested and evaluated in four seasons outdoor environments. The results have shown improved precision–recall performance against the state-of-the-art SeqSLAM algorithm.

show abstract

Section: Methodsmentioning

confidence: 99%

Visual Localization across Seasons Using Sequence Matching Based on Multi-Feature Combination

Qiao

Cappelle

Ruichek

2017

Sensors

View full text Add to dashboard Cite

show abstract

“…H.263/MPEG-4 is suited for parallel processing as it contains both fine-grained and coarse-grained parallelism. Although the use of hardware acceleration units as reported in [4,5] can achieve high encoding performance, hardware is also less flexible and unsuitable for frequent updates when compared with software only implementations. Recent work by [6] has achieved real-time MPEG-4 video encoding of the 15 fps QCIF size images requiring 65.7 MCycles using the same RISC embedded processor as we use in our case.…”

Section: Introductionmentioning

confidence: 99%

Customizing Multiprocessor Implementation of an Automated Video Surveillance System

Wang¹,

Salčić²,

Biglari-Abhari³

2006

EURASIP Journal on Embedded Systems

View full text Add to dashboard Cite

This paper reports on the development of an automated embedded video surveillance system using two customized embedded RISC processors. The application is partitioned into object tracking and video stream encoding subsystems. The real-time object tracker is able to detect and track moving objects by video images of scenes taken by stationary cameras. It is based on the block-matching algorithm. The video stream encoding involves the optimization of an international telecommunications union (ITU)-T H.263 baseline video encoder for quarter common intermediate format (QCIF) and common intermediate format (CIF) resolution images. The two subsystems running on two processor cores were integrated and a simple protocol was added to realize the automated video surveillance system. The experimental results show that the system is capable of detecting, tracking, and encoding QCIF and CIF resolution images with object movements in them in real-time. With low cycle-count, low-transistor count, and low-power consumption requirements, the system is ideal for deployment in remote locations.

show abstract