Autonomous vehicles must detect nearby road users quickly and reliably, even when objects are partly hidden. We developed a lightweight camera-based method that adapts its processing to scene difficulty, combines information across video frames, and learns from laser-sensor data during training. It reached 38.7% on the benchmark detection measure and processed 26.2 frames per second without laser sensors during use, showing strong potential for fast, lower-cost vehicle perception.

We developed a fast and compact model to detect pedestrians in crowded scenes, especially when people are partly hidden or far away. Our method improves how the model learns from small and difficult cases, and how it balances speed and accuracy. It runs much faster than current systems while maintaining similar accuracy, making it suitable for real-time use on mobile and edge devices.