Dense Continuous-Time Optical Flow From Event Cameras.

We present a method for estimating dense continuous-time optical flow from event data. Traditional dense optical flow methods compute the pixel displacement between two images. Due to missing information, these approaches cannot recover the pixel trajectories in the blind time between two images. In this work, we show that it is possible to compute per-pixel, continuous-time optical flow using events from an event camera. Events provide temporally fine-grained information about movement in pixel space due to their asynchronous nature and microsecond response time. We leverage these benefits to predict pixel trajectories densely in continuous time via parameterized Bézier curves. To achieve this, we build a neural network with strong inductive biases for this task: First, we build multiple sequential correlation volumes in time using event data. Second, we use Bézier curves to index these correlation volumes at multiple timestamps along the trajectory. Third, we use the retrieved correlation to update the Bézier curve representations iteratively. Our method can optionally include image pairs to boost performance further. To the best of our knowledge, our model is the first method that can regress dense pixel trajectories from event data. To train and evaluate our model, we introduce a synthetic dataset (MultiFlow) that features moving objects and ground truth trajectories for every pixel. Our quantitative experiments not only suggest that our method successfully predicts pixel trajectories in continuous time but also that it is competitive in the traditional two-view pixel displacement metric on MultiFlow and DSEC-Flow. Open source code and datasets are released to the public.

AlphaPilot: autonomous drone racing.

This paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The system has successfully been deployed at the first autonomous drone racing world championship: the 2019 AlphaPilot Challenge. Contrary to traditional drone racing systems, which only detect the next gate, our approach makes use of any visible gate and takes advantage of multiple, simultaneous gate detections to compensate for drift in the state estimate and build a global map of the gates. The global map and drift-compensated state estimate allow the drone to navigate through the race course even when the gates are not immediately visible and further enable to plan a near time-optimal path through the race course in real time based on approximate drone dynamics. The proposed system has been demonstrated to successfully guide the drone through tight race courses reaching speeds up to 8 m / s and ranked second at the 2019 AlphaPilot Challenge.

Massive inborn angiogenesis in the brain scarcely raises cerebral blood flow.

The functional consequences of increased capillary densities in the brain resulting from vascular endothelial growth factor (VEGF165) overexpression are unknown. Therefore, the authors measured local CBF using the iodo-[14C]antipyrine technique in transgenic mice expressing brain-specifically sixfold higher VEGF165 levels and in nontransgenic littermates. To reveal possible compensatory vasoconstriction, CBF was also measured during severe hypercapnia (Paco2 > 130 mm Hg). Simultaneously, local capillary density, perfusion state, and blood-brain-barrier permeability were assessed. Using the 2-[14C]deoxyglucose method, metabolic effects of VEGF over-expression could be excluded. In transgenic mice all capillaries showed normal morphology and a tight blood-brain barrier. However, 3% nonperfused capillaries in some brain structures indicate ongoing angiogenesis. Capillary density was drastically increased in transgenic mice in white matter structures (70% to 185%), the dentate gyrus (143%), and caudate nucleus (86%). In all other brain structures investigated, capillary densities were moderately increased by approximately 20%. Normocapnic CBF did not differ between transgenic and nontransgenic mice. During maximal hypercapnic vasodilation, CBF was 20% to 30% higher in transgenic mice, although only in brain structures where capillary density was increased more than twofold. These findings suggest that attenuated CBF in transgenic mice during normocapnia is only partly due to a compensatory vasoconstriction, and that microvascular networks in transgenic brains might be ineffectively constructed.