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

We aim to detect and identify multiple objects using multiple cameras andcomputer vision for disaster response drones. The major challenges are tamingdetection errors, resolving ID switching and fragmentation, adapting tomulti-scale features and multiple views with global camera motion. Two simpleapproaches are proposed to solve these issues. One is a fast multi-camerasystem that added a tracklet association, and the other is incorporating ahigh-performance detector and tracker to resolve restrictions. (...) Theaccuracy of our first approach (85.71%) is slightly improved compared to ourbaseline, FairMOT (85.44%) in the validation dataset. In the final resultscalculated based on L2-norm error, the baseline was 48.1, while the proposedmodel combination was 34.9, which is a great reduction of error by a margin of27.4%. In the second approach, although DeepSORT only processes a quarter ofall frames due to hardware and time limitations, our model with DeepSORT(42.9%) outperforms FairMOT (71.4%) in terms of recall. Both of our modelsranked second and third place in the `AI Grand Challenge' organized by theKorean Ministry of Science and ICT in 2020 and 2021, respectively. The sourcecodes are publicly available at these URLs(github.com/mlvlab/drone_ai_challenge, github.com/mlvlab/Drone_Task1,github.com/mlvlab/Rony2_task3, github.com/mlvlab/Drone_task4).

Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones