Recent advancements in intelligent transportation systems have enabled smart vehicles to autonomously detect, predict, and respond to potential hazards in real time. However, achieving sub-second reaction performance remains challenging due to computational latency in sensor data processing. This paper presents an adaptive parallel processing framework that integrates multi-core concurrency and adjustable spatial down-sampling (compression) for real-time multi-vehicle collision prevention. We benchmark four operating modes (sequential/parallel × compressed/uncompressed) on a 22-thread CPU platform. Compared to the sequential uncompressed baseline, the proposed fork-compress mode reduces end-to-end pipeline latency by approximately 66%. Compared to the sequential compressed baseline, the reduction is smaller (≈24%), highlighting the importance of explicitly stating the baseline for headline claims. The scalability analysis is based on Amdahl’s Law and indicates an effective parallelizable fraction of about 25% under our implementation, with the remaining time dominated by I/O, synchronization, and coordination overhead. We define compression factor k as linear spatial down-sampling where both image width and height are divided by k (pixel area reduced to 1/k2). Empirical results show that moderate down-sampling (around k ≈ 4–6) provides the best latency–accuracy trade-off. A supporting detection study using YOLOv4-tiny on BDD100K demonstrates that down-sampling can significantly reduce mAP if the model is not retrained, and that compression-aware fine-tuning partially recovers the lost accuracy.
Zhao et al. (Sun,) studied this question.