Skip to content

haniruth/GeoVehicle-ReID

Repository files navigation

GeoVehicle-ReID

Geometry-aware vehicle re-identification on the VeRi dataset. This project extends a standard ResNet vehicle ReID pipeline with local part descriptors, a pseudo-depth/visibility attention branch, BNNeck retrieval features, camera auxiliary supervision, and optional flip-consistency training.

Project Summary

  • Implemented a geometry-aware ReID model registered as geovehicle_resnet18, geovehicle_resnet34, and geovehicle_resnet50.
  • Trained with identity classification and hard triplet loss for retrieval-oriented embeddings.
  • Added local horizontal part descriptors to retain vehicle identity cues such as lights, windows, roof shape, wheels, and color regions.
  • Added a pseudo-depth/visibility branch to improve viewpoint-sensitive retrieval.
  • Evaluated using CMC and mAP on VeRi query/gallery retrieval.

Verified Results

Model Dataset mAP Rank-1 Rank-5 Rank-10
GeoVehicle ResNet-18 VeRi 60.2% 84.7% 94.3% 96.4%

The verified run used geovehicle_resnet18, ImageNet pretraining, RandomIdentitySampler, 4 instances per identity, AMSGrad, batch size 64, camera auxiliary loss, flip consistency, L2-normalized features, and flip-test evaluation.

Repository Layout

  • main.py: training and evaluation entry point.
  • args.py: command-line options.
  • src/models/geovehicle.py: geometry-aware ReID architecture.
  • src/losses/: cross-entropy and hard triplet losses.
  • src/eval_metrics.py: CMC and mAP retrieval metrics.
  • train_geovehicle_resnet18.sh: main reproduced training command.
  • run_geovehicle_ablation.sh: ablation runner for model components.
  • docs/geovehicle_reid.md: method notes and ablation guidance.
  • results/verified_results.md: compact result record.

Data And Weights

The VeRi dataset and trained checkpoints are not included. Set DATA_ROOT to the dataset root before running scripts.

DATA_ROOT=/path/to/veri-dataset-root bash train_geovehicle_resnet18.sh

Notes

This project does not claim metric 3D reconstruction from VeRi. The geometry branch is a pseudo-3D/visibility representation designed to improve viewpoint-aware vehicle retrieval when calibrated 3D geometry is unavailable.

About

Geometry-aware vehicle re-identification on VeRi using local part descriptors, BNNeck retrieval features, pseudo-depth attention, and camera supervision.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors