Depth Estimation fusing Image and Radar Measurements with Uncertain Directions

• Published in: 2024 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 6
• Main Authors: Kotani, Masaya, Oba, Takeru, Ukita, Norimichi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 30.06.2024
• Subjects: Depth maps; Estimation; Fusion; Laser radar; Measurement uncertainty; Radar measurement depths; Radar measurements; Training; Training data; Uncertainty
• ISSN: 2161-4407
• DOI: 10.1109/IJCNN60899.2024.10650484

This paper proposes a depth estimation method using radar-image fusion by addressing the uncertain vertical directions of sparse radar measurements. In prior radar-image fusion work, image features are merged with the uncertain sparse depths measured by radar through convolutional layers. This approach is disturbed by the features computed with the uncertain radar depths. Furthermore, since the features are computed with a fully convolutional network, the uncertainty of each depth corresponding to a pixel is spread out over its surrounding pixels. Our method avoids this problem by computing features only with an image and conditioning the features pixelwise with the radar depth. Furthermore, the set of possibly correct radar directions is identified with reliable LiDAR measurements, which are available only in the training stage. Our method improves training data by learning only these possibly correct radar directions, while the previous method trains raw radar measurements, including erroneous measurements. Experimental results demonstrate that our method can improve the quantitative and qualitative results compared with its base method using radar-image fusion.