DYNAMIC CALIBRATION SYSTEM AND DYNAMIC CALIBRATION METHOD FOR HETEROGENEOUS SENSORS

    公开(公告)号:US20240142270A1

    公开(公告)日:2024-05-02

    申请号:US18154000

    申请日:2023-01-12

    IPC分类号: G01C25/00

    CPC分类号: G01C25/00

    摘要: A dynamic calibration method for heterogeneous sensors includes: sensing dynamic objects by a first sensor to generate first sensing data; sensing the dynamic objects by a second sensor to generate second sensing data; performing feature matching between the first sensing data and the second sensing data to determine first valid data and second valid data, and identifying a tracked object from the dynamic objects based on the first valid data and the second valid data; performing feature comparison between the first valid data and the second valid data corresponding to the tracked object to calculate data errors between the first sensor and the second sensor; and calculating a calibration parameter based on the first valid data and the second valid data when the number of the data errors exceeds an error threshold, and adjusting the first sensing data and the second sensing data based on the calibration parameter.

    Dynamic multi-mode CNN accelerator and operating methods

    公开(公告)号:US11645365B2

    公开(公告)日:2023-05-09

    申请号:US16731695

    申请日:2019-12-31

    摘要: A convolutional neural network (CNN) operation accelerator comprising a first sub-accelerator and a second sub-accelerator is provided. The first sub-accelerator comprises I units of CNN processor cores, J units of element-wise & quantize processors, and K units of pool and nonlinear function processor. The second sub-accelerator comprises X units of CNN processor cores, Y units of first element-wise & quantize processors, and Z units of pool and nonlinear function processor. The above variables I˜K, X˜Z are all greater than 0, and at least one of the three relations, namely, “I is different from X”, “J is different from Y”, and “K is different from Z”, is satisfied. A to-be-performed CNN operation comprises a first partial CNN operation and a second partial CNN operation. The first sub-accelerator and the second sub-accelerator perform the first partial CNN operation and the second partial CNN operation, respectively.