Abstract: An object detection network can be trained with training images to identify and classify objects in images from a sensor system disposed on a maritime vessel. The objects in the images can be identified, classified, and heat maps can be generated. Instructions can be sent regarding operation of the maritime vessel. For some training images, water conditions, sky conditions, and/or light conditions in the image can be changed to generate a second image.

Abstract: A support structure includes a mounting pole and a mounting frame supported by the mounting pole. The mounting frame includes a vertical base and a horizontal arm projecting away from the vertical base in a first direction. The support structure further includes a first and second camera mount coupled to the vertical base, and a LIDAR mount and a radar mount coupled to the horizontal arm. An omnidirectional camera is coupled to the first camera mount and extends a first distance away from the mounting frame in a first direction that is perpendicular to the vertical base of the mounting frame. A thermal camera is coupled to the second camera mount and oriented in the first direction. A LIDAR unit is coupled to the LIDAR mount, and a radar unit is coupled to the radar mount.

Abstract: Disclosed herein are systems, methods, and apparatuses for deep learning and intelligent sensing system integrations. A processor may be configured to receive a plurality of images from the sensor system, identify objects in the images in an offline mode, classify the objects in the images in the offline mode, generate heat maps in the offline mode, and send instructions regarding operation of the maritime vessel based on the objects that are identified. The visual sensor may be a stereoscopic camera. The processor may be further configured to perform stereoscopy. The instructions may include a speed or a heading of, for example, a maritime vessel.

Abstract: The present disclosure may be embodied as an optical encoder system comprising a first optical sensor, a second optical sensor, a first up-down counter, a second up-down counter, and an I/O expander. The optical encoder system may further include a buffer. The present disclosure may also be embodied as an optical encoder system comprising an optical encoder, and a monostable multivibrator. The present disclosure may also be embodied as a method for encoding optical data comprising generating a first optical sensor signal and a second optical sensor signal, converting the first optical sensor signal and second optical sensor signal into four first counter signals, generating a borrow output signal and a carry output signal, converting the borrow output signal and the carry output signal into four second counter signals, and converting the first counter signals and second counter signals into a serial data signal and a serial clock signal.

Abstract: The present disclosure provides a sensor system and method of operating the same. The sensor system includes a data collection mast including a base, a support member, a main member, a top plate, a first enclosure, a second enclosure, a first cantilever member, and a second cantilever member. The sensor system further includes a pair of stereoscopic cameras disposed on the main member extending through the second enclosure, a radar system disposed on the top plate, a compass disposed on the second cantilever member, a LIDAR unit disposed on the first cantilever member, and a control unit disposed on the main member within the first enclosure. Each of the pair of stereoscopic cameras, radar system, compass, and LIDAR unit are in electronic communication with the control unit, such that control unit receive the data collected from each sensor.