Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues

Abstract

Today's state-of-the-art methods for 3D object detection are based on lidar, stereo, or monocular cameras. Lidar-based methods achieve the best accuracy, but have a large footprint, high cost, and mechanically-limited angular sampling rates, resulting in low spatial resolution at long ranges. Recent approaches based on low-cost monocular or stereo cameras promise to overcome these limitations but struggle in low-light or low-contrast regions as they rely on passive CMOS sensors. In this work, we propose a novel 3D object detection modality that exploits temporal illumination cues from a low-cost monocular gated imager. We propose a novel deep detector architecture, Gated3D, that is tailored to temporal illumination cues from three gated images. Gated images allow us to exploit mature 2D object feature extractors that guide the 3D predictions through a frustum segment estimation. We assess the proposed method on a novel 3D detection dataset that includes gated imagery captured in over 10,000 km of driving data. We validate that our method outperforms state-of-the-art monocular and stereo approaches at long distances. We will release our code and dataset, opening up a new sensor modality as an avenue to replace lidar in autonomous driving.

Unconventional Visual Sensors for Autonomous Vehicles

“…The dataset covers snow, rain, urban and sub-urban scenarios. The DENSE dataset is further annotated in Julca-Aguilar et al [116] as Gated3D dataset, in which more than 100K objects in 4 classes are manually annotated over 12997 image frames. Based on these datasets, Tobias et al [117] present a deep neural networks (DNN) named as "gated2depth", which can estimate th1e depth of each pixel in the range-gated camera.…”

“…A delicate feature exchange network is designed to dynamically allocate the best features for each sensor. To explore the implied range information in the slice images, Julca-Aguilar et al [116] propose a DNN for 3D object detection. The proposed DNN is tailored to the temporal illumination cues from the three image slices.…”