Abstract:
An aircraft-based infrared image recognition device for a ground moving target, including an infrared non-uniformity correction module, an image rotation module, an image registration module, a multi-level filtering module, a connected domain labeling module, a target detection and feature recognition module, a process control module, and a FPGA-based interconnection module. The invention uses an ASIC/SoC chip for image processing and target recognition, the DSP processor and the FPGA processor, it is possible to enable a multi-level image processing and target recognition algorithm, to improve system parallel, and to facilitate an aircraft-based infrared image recognition method for a ground moving target. Meanwhile, embodiments of the invention effectively reduce power consumption of the device.
Abstract:
A complex surface three-coordinate measuring device includes a three-degree-of-freedom motion platform and a force control probe, the force control probe is fixedly mounted on the Z-axis sliding block, which is in the same direction as the X-axis direction and used to contact with the workpiece surface with constant force. A six-axis force sensor is used to collect the contact force between the stylus and the workpiece surface. In this method, the force control is realized in the measurement to make the stylus in constant force contact with the workpiece surface. The error compensation direction is determined according to the direction of the contact force, and then the effective radius of the stylus spherical head is compensated in this direction, thus the actual contact point of stylus and workpiece can be obtained.
Abstract:
A method for detecting spectral characteristics of multi-band moving objects. The method includes: 1) dividing a full field of view into several subfields of view, and scanning and extracting suspected objects in each subfield one by one; 2) correlating interrelated suspected objects in adjacent subfields via coordinates to determine objects of interest that exist in the full field of view; 3) calculating the speeds of the objects of interest; 4) calculating average speed of all of the objects of interest and classifying the objects of interest according to their average speed; 5) compensating and rectifying the objective spectrum obtained from calculation; and 6) matching the compensated and rectified objective spectrum with a spectrum fingerprint database whereby realizing recognition of the multi-band moving objects.