English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents an object recognition approachof outdoor autonomous systems identifying the nature of theinterested object when observing an image. Therefore, seekingfor effective and robust recognition method, the proposedapproach is performed using a novel saliency based featuredetector/descriptor which is combined with an object classifierto identify the nature of objects in an indoor or an outdoorenvironment. As known, bottom-up visual attention computationalmodels need a considerable computational power andcommunication cost. A major challenge in this work is to dealwith such image processing applications managing a large amountof the information processing and to work within real-timerequirements by improving the processing speed.Based on interesting approach designing specific architecturesfor parallelism, this paper presents a solution for rapidprototyping of saliency-based object recognition applications. Inorder to meet computation and communication requirement,the developed pipelined architectures are composed of identicalprocessing modules which can work concurrently with distributedmemories and compute in parallel several sequential tasks with ahigh computational cost. We present hardware implementationswith performance results on an Xilinx System-on-ProgrammableChip (SoPC) target. The experimental results including executiontimes and application speedups as well as requirements in termsof computing resources show that the proposed homogeneousnetwork of processors is efficient for embedding the proposedimage processing application.

A Bottom-up Approach for Visual Object Recognition on FPGA based Embedded Multiprocessor Architecture