Abstract: The present disclosure provides a method and system architectures for carrying out the method of automated marine life object classification and identification utilising a core of a Deep Neural Network, DNN, to facilitate the operations of a post-processing module subnetwork such as instance segmentation, masking, labelling, and image overlay of an input image determined to contain one or more target marine life objects. Multiple instances of target objects from the same image data can be easily classified and labelled for post-processing through application of a masking layer over each respective object by a semantic segmentation network.

Abstract: A bracket, a module assembly, and an electronic device, so as to improve position stability of the module in the electronic device. Two first limiting parts arranged opposite to each other are arranged at two ends of the bracket, a second limiting part is arranged on at least one side of the bracket, and the two first limiting parts and the second limiting part are enclosed to form a mounting position for mounting the module. Both the first limiting parts and the second limiting part may limit the module, so as to limit in all directions and ensure position stability of the module in the bracket. The bracket is further fixed to the electronic device through fixing parts, so that the position stability of the module in the electronic device may be improved.

Abstract: The present disclosure provides an integrated collection, filtration, and analysis system which is configured to automatically collect fluid samples from a surrounding open water environment, isolate floating particles of a target size range, and perform analysis on the collected particles in-situ. The particles may also be filtered by one or more parameters other than size, and also provided herein is a two-stage vortex filter specially adapted to isolate floating particles of a desired density range from a fluid.

Abstract: An automated grasping apparatus for precise and clean assembly of a large-aperture optical element includes a reconfigurable end effector, a manipulating robot arm, a computer control unit, a task management software and process database system, a code scanning recognizer, and an electrical auxiliary support system. During an assembling operation, a code of the optical element is scanned by the code scanning recognizer, wherein a suitable process for the optical element is retrieved automatically. The configuration of the end effector is adjusted according to an instruction flow that precision grasping and stable suction of the optical element are achieved by manipulating the end effector. The robot arm is moved to place the optical element at a designated station, and the robot arm carries the end effector to return to an original position after the assembly operation is completed.

Abstract: An automated grasping apparatus for precise and clean assembly of a large-aperture optical element includes a reconfigurable end effector, a manipulating robot arm, a computer control unit, a task management software and process database system, a code scanning recognizer, and an electrical auxiliary support system. During an assembling operation, a code of the optical element is scanned by the code scanning recognizer, wherein a suitable process for the optical element is retrieved automatically. The configuration of the end effector is adjusted according to an instruction flow that precision grasping and stable suction of the optical element are achieved by manipulating the end effector. The robot arm is moved to place the optical element at a designated station, and the robot arm carries the end effector to return to an original position after the assembly operation is completed.