XWOD: A Real-World Benchmark for Object Detection under Extreme Weather Conditions

Autonomous driving and intelligent transportation systems remain vulnerable under extreme weather. The U.S. Federal Highway Administration reports that roughly 745,000 crashes and 3,800 fatalities per year are weather-related, and recent regulatory investigations have examined failures of Level-2/3 driving systems under reduced-visibility conditions. However, datasets commonly used to evaluate weather robustness remain limited in scale, diversity, and realism. In this paper, we introduce XWOD (Extreme Weather Object Detection), a large-scale real-world traffic-object detection benchmark containing 10,010 images and 42,924 bounding boxes across seven extreme weather conditions: rain, snow, fog, haze/sand/dust, flooding, tornado, and wildfire. The dataset covers six traffic-object categories, including car, person, truck, motorcycle, bicycle, and bus. XWOD extends the weather taxonomy from one to seven conditions, and is the first to cover the emerging class of climate-amplified hazards, such as flooding, tornado, and wildfire. To evaluate the quality of our data, we train standard YOLO-family detectors on XWOD and test them zero-shot on external weather benchmarks, achieving mAP$_{50}$ scores of 63.00% on RTTS, 59.94% on DAWN, and 61.12% on WEDGE, compared with the corresponding published YOLO-based baselines of 40.37%, 32.75%, and 45.41%, respectively, representing relative improvements of 56%, 83%, and 35%. These cross-dataset results show that XWOD provides a strong source domain for learning weather-robust traffic perception. We release the dataset, splits, baseline weights, and reproducible evaluation code under a research-use license.

GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction

Predicting the future trajectories of pedestrians on the road is an important task for autonomous driving. The pedestrian trajectory prediction is affected by scene paths, pedestrian's intentions and decision-making, which is a multi-modal problem. Most recent studies use past trajectories to predict a variety of potential future trajectory distributions, which do not account for the scene context and pedestrian targets. Instead of predicting the future trajectory directly, we propose to use scene context and observed trajectory to predict the goal points first, and then reuse the goal points to predict the future trajectories. By leveraging the information from scene context and observed trajectory, the uncertainty can be limited to a few target areas, which represent the "goals" of the pedestrians. In this paper, we propose GoalNet, a new trajectory prediction neural network based on the goal areas of a pedestrian. Our network can predict both pedestrian's trajectories and bounding boxes. The overall model is efficient and modular, and its outputs can be changed according to the usage scenario. Experimental results show that GoalNet significantly improves the previous state-of-the-art performance by 48.7% on the JAAD and 40.8% on the PIE dataset.