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

Multi-Object Tracking (MOT) is a challenging task in the complex scene suchas surveillance and autonomous driving. In this paper, we propose a noveltracklet processing method to cleave and re-connect tracklets on crowd orlong-term occlusion by Siamese Bi-Gated Recurrent Unit (GRU). The trackletgeneration utilizes object features extracted by CNN and RNN to create thehigh-confidence tracklet candidates in sparse scenario. Due to mis-tracking inthe generation process, the tracklets from different objects are split intoseveral sub-tracklets by a bidirectional GRU. After that, a Siamese GRU basedtracklet re-connection method is applied to link the sub-tracklets which belongto the same object to form a whole trajectory. In addition, we extract thetracklet images from existing MOT datasets and propose a novel dataset to trainour networks. The proposed dataset contains more than 95160 pedestrian images.It has 793 different persons in it. On average, there are 120 images for eachperson with positions and sizes. Experimental results demonstrate theadvantages of our model over the state-of-the-art methods on MOT16.

Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking