Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances
This work addresses the deployment challenge of Lidar object detection in automotive systems, offering a computationally efficient solution for real-time processing on CPU.
The authors tackled the problem of real-time Lidar object classification on CPU for embedded vehicle systems, proposing a method that uses segmented instances and a novel data representation to achieve good results on public data while running in real-time without specific optimization.
Object detection algorithms for Lidar data have seen numerous publications in recent years, reporting good results on dataset benchmarks oriented towards automotive requirements. Nevertheless, many of these are not deployable to embedded vehicle systems, as they require immense computational power to be executed close to real time. In this work, we propose a way to facilitate real-time Lidar object classification on CPU. We show how our approach uses segmented object instances to extract important features, enabling a computationally efficient batch-wise classification. For this, we introduce a data representation which translates three-dimensional information into small image patches, using decomposed normal vector images. We couple this with dedicated object statistics to handle edge cases. We apply our method on the tasks of object detection and semantic segmentation, as well as the relatively new challenge of panoptic segmentation. Through evaluation, we show, that our algorithm is capable of producing good results on public data, while running in real time on CPU without using specific optimisation.