TTC.PA.1581 : ENRICHED AND DISCRIMINATIVE
CONVOLUTIONAL NEURAL
NETWORK FEATURES FOR
PEDESTRIAN RE-IDENTIFICATION
PROBLEM ADDRESSED
Pedestrian re-identification and tracking across multiple cameras with a non-overlapped field of view for continuous retrieval of pedestrian walking trajectories in wide areas .
APPLICATION AREAS
Smart construction
workers’ safety & site analysis
Smart transportation
traffic flow analysis
TECHNOLOGY INNOVATIONS
An approach of explainable CNN design based on feature map visualization
A new CNN to extract discriminative & distributed features for more robust pedestrian ReID
An incremental multi-image feature aggregation mechanism for more robust pedestrian identity matching
(a) ResNet
(b) OSNet
(c) OSNet + BDB-vertical
(d) OSNet + BDB-horizontal
Smart mobility walkability evaluation
Smart retail
behavioural analysis
Smart city
urban design & mobility
Smart warehouse
behavioural/ flow analysis
KEY IMPACTS & ADVANTAGES
Accurate pedestrian tracking
4-8%
improvement over baselines Facilitate future research evaluating CNNs for image processing tasks based on an explainable approach
Timestamp
Cam 6
Cam 7
Cam 1
Enable real-world multi-camera processing to identify pedestrian walking trajectories
GET IN TOUCH
to receive a personalized consultation, discuss research or commercial collaboration opportunities, and more
AI-Powered Construction Site Safety Monitoring System
info@autosafe.ai
+852 6538 6246
Support pedestrian walking behavioral analyses and what-if facility layout evaluation and design optimization