US 11,861,853 B1
System and method of vehicle speed estimation using moving camera and time series neural network
Athul Mathew, Riyadh (SA); Thariq Khalid, Riyadh (SA); and Riad Souissi, Riyadh (SA)
Assigned to ELM, Riyadh (SA)
Filed by ELM, Riyadh (SA)
Filed on Jun. 2, 2023, as Appl. No. 18/328,441.
Claims priority of provisional application 63/426,211, filed on Nov. 17, 2022.
Int. Cl. G06T 7/00 (2017.01); G06T 7/246 (2017.01)
CPC G06T 7/246 (2017.01) [G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30256 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for ego vehicle speed estimation, comprising
a car-mounted monocular camera for capturing a sequence of video frames of an outdoor scene from a moving car, where the outdoor scene includes a road, as a camera channel;
processing circuitry configured with
a single-shot network, and
a neural network time series model,
wherein the single-shot network segments features of the road in the video frame sequence and generates a masked-attention map for the segmented road features;
a concatenation operation that concatenates the masked-attention map as an additional channel to the camera channel to generate a masked-attention input;
wherein the neural network time series model receives the masked-attention input and generates an estimated speed of the ego vehicle based on displacement of the segmented road features in the video sequences; and
output circuitry to output a signal indicating the estimated speed.