Toward The Design of An Efficient Transparent Traffic Environment Based on Vehicular Edge Computing

Sun, Peng; Boukerche, Azzedine

doi:10.1109/globecom46510.2021.9685557

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…system (ITS), that provides a promising solution to troublesome problems including traffic congestion, collision, and emission pollution [1]. With the development of deep learning and computer vision, environmental perception as the essential component of self-driving system, has also made great progress on such object detection [2], [3], [4], [5] and segmentation [6], [7] tasks, receiving substantial performance improvement both on accuracy and efficiency.…”

mentioning

confidence: 99%

See 1 more Smart Citation

V2VFormer++: Multi-Modal Vehicle-to-Vehicle Cooperative Perception via Global-Local Transformer

Yin,

Tian,

Lin

et al. 2024

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Multi-vehicle cooperative perception has recently emerged for facilitating long-range and large-scale perception ability of connected automated vehicles (CAVs). Nonetheless, enormous efforts formulate collaborative perception as LiDARonly 3D detection paradigm, neglecting the significance and complementary of dense image. In this work, we construct the first multi-modal vehicle-to-vehicle cooperative perception framework dubbed as V2VFormer++, where individual camera-LiDAR representation is incorporated with dynamic channel fusion (DCF) at bird's-eye-view (BEV) space and ego-centric BEV maps from adjacent vehicles are aggregated by global-local transformer module. Specifically, channel-token mixer (CTM) with MLP design is developed to capture global response among neighboring CAVs, and position-aware fusion (PAF) further investigate the spatial correlation between each ego-networked map in a local perspective. In this manner, we could strategically determine which CAVs are desirable for collaboration and how to aggregate the foremost information from them. Quantitative and qualitative experiments are conducted on both publicly-available OPV2V and V2X-Sim 2.0 benchmarks, and our proposed V2VFormer++ reports the state-of-the-art cooperative perception performance, demonstrating its effectiveness and advancement. Moreover, ablation study and visualization analysis further suggest the strong robustness against diverse disturbances from real-world scenarios.

show abstract

mentioning

confidence: 99%

“…In summary, the contributions of this work are mainly described as follows: [1] We propose V2VFormer++, the first multi-modal vehicle-to-vehicle cooperative perception framework that consumes heterogeneous modalities from separate vehicle for enhancing multi-agent collaboration performance.…”

mentioning

confidence: 99%