Search papers, labs, and topics across Lattice.
This paper introduces a two-stage geometry-aware localization pipeline that enhances vehicle localization from monocular roadside surveillance cameras by estimating the projection of the vehicle footprint onto the road plane. Utilizing a YOLO26-based detector for vehicle detection and a ResNet34 regression network to predict the corner points of the projected vehicle base, the method significantly reduces localization errors compared to traditional bounding box center approaches. Experiments reveal a 51.8% reduction in mean image-space localization error and substantial improvements in ground-plane localization accuracy, particularly for distant and geometrically challenging vehicles.
Localization errors for vehicles can be reduced by over 50% by accurately projecting their footprints onto the road plane, transforming traffic monitoring capabilities.
Accurate vehicle localization from monocular roadside surveillance cameras is important for intelligent transportation systems, traffic monitoring, and traffic conflict analysis. Standard approaches often estimate vehicle position from the center of the detector bounding box, which can produce large errors due to perspective distortion and parallax, especially for elevated cameras and large vehicles. This paper proposes a two-stage geometry-aware localization pipeline that estimates the projection of the vehicle footprint onto the road plane. First, vehicles are detected using a YOLO26-based detector. Second, a dedicated ResNet34 regression network predicts four corner points corresponding to the projected vehicle base. The final position is computed as the geometric center of the predicted quadrilateral. The method was trained on synthetic data generated in CARLA and fine-tuned on real-world roadside imagery from DAIR-V2X. Experiments on synthetic and real data showed clear improvements over naive bounding-box-center localization. On DAIR-V2X, the mean image-space localization error decreased from 31.77 px to 15.30 px, a 51.8% improvement, while the median error decreased to 4.29 px. Median ground-plane error for medium-range vehicles decreased from 5.52 m to 0.90 m, and for far-range vehicles from 8.67 m to 1.84 m. The results also show that contextual information surrounding the detector bounding box is important for geometric localization. The largest gains were observed for distant vehicles and geometrically challenging cases affected by strong perspective distortion and parallax.
