Abstract: An apparatus and method for data fusion between heterogeneous sensors are disclosed. The method for data fusion between the heterogeneous sensors may include identifying image data and point cloud data for a search area by each of a camera sensor and a LiDAR sensor that are calibrated using a marker board having a hole; recognizing a translation vector determined through calibrating of the camera sensor and the LiDAR sensor; and projecting the point cloud data of the LiDAR sensor onto the image data of the camera sensor using the recognized translation vector to fuse the identified image data and point cloud data.

Abstract: Disclosed are a real-time object detection method and an apparatus therefor. An object detection apparatus may receive an input image, may extract a first feature map from the input image, may detect an object included in the input image based on the first feature map, may extract, from the input image, a second feature map having resolution higher than the resolution of the first feature map, may extract a third feature map from the second feature map based on the region of the detected object, and may redetect the object based on the first feature map and the third feature map.

Abstract: An apparatus and method for data fusion between heterogeneous sensors are disclosed. The method for data fusion between the heterogeneous sensors may include identifying image data and point cloud data for a search area by each of a camera sensor and a LiDAR sensor that are calibrated using a marker board having a hole; recognizing a translation vector determined through calibrating of the camera sensor and the LiDAR sensor; and projecting the point cloud data of the LiDAR sensor onto the image data of the camera sensor using the recognized translation vector to fuse the identified image data and point cloud data.

Abstract: Disclosed are a real-time object detection method and an apparatus therefor. An object detection apparatus may receive an input image, may extract a first feature map from the input image, may detect an object included in the input image based on the first feature map, may extract, from the input image, a second feature map having resolution higher than the resolution of the first feature map, may extract a third feature map from the second feature map based on the region of the detected object, and may redetect the object based on the first feature map and the third feature map.

Abstract: A rotary looper including a base member, a fixed drum installed on the base member and having spiral guide rollers, a pair of pinch rollers and series of lead rollers sequentially disposed at an inputting side of the base member, and a pair of measuring rollers disposed at a discharging side of the base member. The present invention also includes inside basket rollers, a rotary drum disposed around the fixed drum in a manner such that the rotary drum is rotatably driven by a motor via a rail which is wound around rail rollers which are circularly installed on the base member, a lead drum rotatably disposed in a portion of the rotary drum, inside basket guide rollers, outside basket rollers, and outside basket guide rollers spaced apart from the outside basket rollers by a predetermined distance.