High-speed object detection with a single-photon time-of-flight image sensor

TL;DR

This paper demonstrates that convolutional neural networks can enable high-speed, accurate object detection using low-resolution, single-photon time-of-flight imaging, achieving millisecond latency suitable for safety-critical applications.

Contribution

The study introduces a CNN-based approach to overcome resolution limitations in SPAD-based 3D imaging, enabling real-time object detection at high frame rates.

Findings

Achieved 500 FPS with 2 ms exposure times.

CNN processing time less than 1 ms per frame.

Effective detection in low SBR conditions (as low as 0.05).

Abstract

3D time-of-flight (ToF) imaging is used in a variety of applications such as augmented reality (AR), computer interfaces, robotics and autonomous systems. Single-photon avalanche diodes (SPADs) are one of the enabling technologies providing accurate depth data even over long ranges. By developing SPADs in array format with integrated processing combined with pulsed, flood-type illumination, high-speed 3D capture is possible. However, array sizes tend to be relatively small, limiting the lateral resolution of the resulting depth maps, and, consequently, the information that can be extracted from the image for applications such as object detection. In this paper, we demonstrate that these limitations can be overcome through the use of convolutional neural networks (CNNs) for high-performance object detection. We present outdoor results from a portable SPAD camera system that outputs 16-bin photon timing histograms with 64x32 spatial resolution. The results, obtained with exposure times down to 2 ms (equivalent to 500 FPS) and in signal-to-background (SBR) ratios as low as 0.05, point to the advantages of providing the CNN with full histogram data rather than point clouds alone. Alternatively, a combination of point cloud and active intensity data may be used as input, for a similar level of performance. In either case, the GPU-accelerated processing time is less than 1 ms per frame, leading to an overall latency (image acquisition plus processing) in the millisecond range, making the results relevant for safety-critical computer vision applications which would benefit from faster than human reaction times.