3D Object Visibility Prediction in Autonomous Driving
This work addresses a specific perception challenge for autonomous driving systems, but it appears incremental as it adds a new attribute to an existing framework without major methodological shifts.
The paper tackles the problem of predicting 3D object visibility in autonomous driving by introducing a novel attribute and algorithm, which negligibly affects model effectiveness and efficiency while enhancing safety and reliability for downstream tasks.
With the rapid advancement of hardware and software technologies, research in autonomous driving has seen significant growth. The prevailing framework for multi-sensor autonomous driving encompasses sensor installation, perception, path planning, decision-making, and motion control. At the perception phase, a common approach involves utilizing neural networks to infer 3D bounding box (Bbox) attributes from raw sensor data, including classification, size, and orientation. In this paper, we present a novel attribute and its corresponding algorithm: 3D object visibility. By incorporating multi-task learning, the introduction of this attribute, visibility, negligibly affects the model's effectiveness and efficiency. Our proposal of this attribute and its computational strategy aims to expand the capabilities for downstream tasks, thereby enhancing the safety and reliability of real-time autonomous driving in real-world scenarios.