Hybrid CNN–GCN network with dynamic gating and scale-aware preprocessing for pedestrian crossing intention prediction in Indian road conditions
Rajesh Kannan Megalingam, Naveen Prasaad Selvarajan · 2026
Read Hybrid CNN–GCN network with dynamic gating and scale-aware preprocessing for pedestrian crossing intention prediction in Indian road conditions by Rajesh Kannan Megalingam, Naveen Prasaad Selvarajan (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13538379.txt.
Description
Rajesh Kannan Megalingam and Naveen Prasaad Selvarajan present a hybrid network for predicting pedestrian crossing intent on Indian roads in a 2026 study. Crowded, unstructured streets with frequent blocking views and rule-bending walkers challenge models trained abroad. The design mixes image and graph networks with a gate that shifts weight between visual and motion clues by scene, plus a pose tool tuned for distant or partly hidden walkers. A new local road collection supports testing.
Accuracy reached moderate levels on both a standard foreign collection and the new Indian collection, with the fastest response times among compared methods. Extra tests covered blocked views, walker sizes, and cross-collection transfer, plus a run on a small onboard computer showing near real-time speed. The authors argue the trade-off suits driverless use in messy traffic.
Catalog record
| CREATOR | Rajesh Kannan Megalingam, Naveen Prasaad Selvarajan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 111503 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |