ABMOF: A Novel Optical Flow Algorithm for Dynamic Vision Sensors
This addresses the need for efficient optical flow in high-speed robotics and autonomous systems using DVS, though it is incremental as it adapts existing block-matching techniques to event data.
The paper tackles the problem of computing optical flow from Dynamic Vision Sensors (DVS) event streams, which are not well-suited for conventional algorithms, by proposing ABMOF, an adaptive block-matching method that achieves comparable accuracy to Lucas-Kanade on natural scenes with fast motion up to 30,000 pixels per second.
Dynamic Vision Sensors (DVS), which output asynchronous log intensity change events, have potential applications in high-speed robotics, autonomous cars and drones. The precise event timing, sparse output, and wide dynamic range of the events are well suited for optical flow, but conventional optical flow (OF) algorithms are not well matched to the event stream data. This paper proposes an event-driven OF algorithm called adaptive block-matching optical flow (ABMOF). ABMOF uses time slices of accumulated DVS events. The time slices are adaptively rotated based on the input events and OF results. Compared with other methods such as gradient-based OF, ABMOF can efficiently be implemented in compact logic circuits. Results show that ABMOF achieves comparable accuracy to conventional standards such as Lucas-Kanade (LK). The main contributions of our paper are new adaptive time-slice rotation methods that ensure the generated slices have sufficient features for matching,including a feedback mechanism that controls the generated slices to have average slice displacement within the block search range. An LK method using our adapted slices is also implemented. The ABMOF accuracy is compared with this LK method on natural scene data including sparse and dense texture, high dynamic range, and fast motion exceeding 30,000 pixels per second.The paper dataset and source code are available from http://sensors.ini.uzh.ch/databases.html.