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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the expansive aging of global population, service robot with livingassistance applied in indoor scenes will serve as a crucial role in the fieldof elderly care and health in the future. Service robots need to detectmultiple targets when completing auxiliary tasks. However, indoor scenes areusually complex and there are many types of interference factors, leading togreat challenges in the multiple targets detection. To overcome this technicaldifficulty, a novel improved Mask RCNN method for multiple targets detection inthe indoor complex scenes is proposed in this paper. The improved modelutilizes Mask RCNN as the network framework. On this basis, Convolutional BlockAttention Module (CBAM) with channel mechanism and space mechanism isintegrated, and the influence of different background, distance, angle andinterference factors are comprehensively considered. Meanwhile, in order toevaluate the detection and identification effects of the established model, acomprehensive evaluation system based on loss function and Mean AveragePrecision (mAP) is established. For verification, experiments on the detectionand identification effects under different distances, backgrounds, angles andinterference factors were conducted. The results show that designed modelimproves the accuracy to a higher level and has a better anti-interferenceability than other methods when the detection speed was nearly the same.

A Novel Improved Mask RCNN for Multiple Targets Detection in the Indoor Complex Scenes