Abstract: A surface adaptation method suitable for a vehicle includes evaluating a plurality of longitudinal forces with respect to a plurality of sampling points, evaluating a plurality of wheel slips with respect to the plurality of sampling points, determining a maximum longitudinal force from the plurality of longitudinal forces, and determining a wheel slip threshold from the plurality of wheel slips. The wheel slip threshold corresponds to the maximum longitudinal force.

Abstract: An image adaptive feature extraction method includes dividing an image into a plurality of blocks, performing a feature extraction processing on the plurality of blocks, and obtaining a block feature from each of the plurality of blocks after the feature extraction processing; calculating each block feature by means of a support vector machine (SVM) classifier, wherein each block feature is calculated to obtain a hyperplane normal vector; setting a threshold value, determining the block feature according to the hyperplane normal vector, recording the block as an adaptive feature block when a value of the hyperplane normal vector is higher than the threshold value, and integrating each adaptive feature block to form an adaptive feature image. Because an image adaptive feature extraction process is performed before a pedestrian image detection is calculated, and effective feature data is then selected, computational efficiency is boosted and detection pedestrian error probability is reduced.

Abstract: A surface adaptation method suitable for a vehicle includes evaluating a plurality of longitudinal forces with respect to a plurality of sampling points, evaluating a plurality of wheel slips with respect to the plurality of sampling points, determining a maximum longitudinal force from the plurality of longitudinal forces, and determining a wheel slip threshold from the plurality of wheel slips. The wheel slip threshold corresponds to the maximum longitudinal force.

Abstract: A method for performing pedestrian detection with aid of light detection and ranging (LIDAR) is provided. The method includes: obtaining 3-dimensional (3D) point cloud data through the LIDAR; performing ground separation processing on the 3D point cloud data to remove ground information; performing object extraction processing on the 3D point cloud data to obtain 3D point cloud chart that includes pedestrian candidate point cloud group; performing 2-dimensional (2D) mapping processing on the 3D point cloud chart to obtain 2D chart; and extracting 3D feature and 2D feature from the 3D point cloud chart and the 2D chart, respectively, and utilizing the 3D feature and the 2D feature to determine location of the pedestrian. According to the method, image data obtained by the LIDAR may be enhanced, the method may distinguish between pedestrian far away and environment blocks, and pedestrian recognition in nighttime or in bad weather may be improved.

Abstract: A vehicle detection method includes acquiring a three-dimensional (3D) image with a plurality of point clouds; mapping the 3D image onto a two-dimensional (2D) image; interpolating the 2D image according to a distance between a camera and a first point cloud of the plurality of point clouds; transforming the 3D image into a plurality of voxels, and extracting a plurality of 3D deep features and a plurality of 2D deep features according to the plurality of voxels; and determining a detection result according to a classification of the plurality of 3D deep features and the plurality of 2D deep features.

Abstract: An image adaptive feature extraction method includes dividing an image into a plurality of blocks, performing a feature extraction processing on the plurality of blocks, and obtaining a block feature from each of the plurality of blocks after the feature extraction processing; calculating each block feature by means of a support vector machine (SVM) classifier, wherein each block feature is calculated to obtain a hyperplane normal vector; setting a threshold value, determining the block feature according to the hyperplane normal vector, recording the block as an adaptive feature block when a value of the hyperplane normal vector is higher than the threshold value, and integrating each adaptive feature block to form an adaptive feature image. Because an image adaptive feature extraction process is performed before a pedestrian image detection is calculated, and effective feature data is then selected, computational efficiency is boosted and detection pedestrian error probability is reduced.

Abstract: A method for extracting features of a thermal image is provided. The method includes: reading a thermal image, and dividing the thermal image into a plurality of block images; and extracting a histogram of oriented gradient (HOG) feature histogram from each of the plurality of block images, and transforming the HOG feature histogram of each of the plurality of block images into a symmetric weighting HOG (SW-HOG) feature histogram. The SW-HOG feature histogram is obtained by multiplying a histogram of gradient intensity distribution by a block weighting. The method increases weightings of blocks which cover human contours and reduces weightings of blocks of an internal region of a human appearance through analyzing thermal lightness difference of regions within blocks, to reduce the influence of clothes in the internal region and the influence of the background region.

Abstract: A method for performing pedestrian detection with aid of light detection and ranging (LIDAR) is provided. The method includes: obtaining 3-dimensional (3D) point cloud data through the LIDAR; performing ground separation processing on the 3D point cloud data to remove ground information; performing object extraction processing on the 3D point cloud data to obtain 3D point cloud chart that includes pedestrian candidate point cloud group; performing 2-dimensional (2D) mapping processing on the 3D point cloud chart to obtain 2D chart; and extracting 3D feature and 2D feature from the 3D point cloud chart and the 2D chart, respectively, and utilizing the 3D feature and the 2D feature to determine location of the pedestrian. According to the method, image data obtained by the LIDAR may be enhanced, the method may distinguish between pedestrian far away and environment blocks, and pedestrian recognition in nighttime or in bad weather may be improved.

Abstract: A method for extracting features of a thermal image is provided. The method includes: reading a thermal image, and dividing the thermal image into a plurality of block images; and extracting a histogram of oriented gradient (HOG) feature histogram from each of the plurality of block images, and transforming the HOG feature histogram of each of the plurality of block images into a symmetric weighting HOG (SW-HOG) feature histogram. The SW-HOG feature histogram is obtained by multiplying a histogram of gradient intensity distribution by a block weighting. The method increases weightings of blocks which cover human contours and reduces weightings of blocks of an internal region of a human appearance through analyzing thermal lightness difference of regions within blocks, to reduce the influence of clothes in the internal region and the influence of the background region.

Abstract: A method of speeding up image detection, adapted to increase a speed of detecting a target image and enhance efficiency of image detection, comprises the steps of capturing an image; retrieving a plurality of characteristic points of the image; creating a region of interest (ROI) centered at the characteristic points each; creating a plurality of search point scan windows corresponding to the ROIs, respectively; calculating target hit scores of the characteristic points and the search point scan windows; comparing the target hit scores of the characteristic points and the search point scan windows to obtain an ROI most likely to have a target image; calculating centroid coordinates of the ROI by a centroid shift weight equation; and narrowing a scope of ROI search according to a location of the centroid coordinates and reducing a displacement between the search points.

Abstract: An all-weather thermal-image pedestrian detection method includes (a) capturing diurnal thermal images and nocturnal thermal images of a same pedestrian and non-pedestrian object in a same defined block to create a sample database of thermal images, wherein the sample database comprises pedestrian samples and non-pedestrian samples; (b) performing LBP encoding on the pedestrian samples and the non-pedestrian samples, wherein complementary LBP codes in the same defined block are treated as identical LBP codes; (c) expressing the LBP codes in the same defined block as features by a gradient direction histogram (HOG) to obtain feature training samples of the pedestrian samples and the non-pedestrian samples; (d) entering the feature training samples into a SVM to undergo training by Adaboost so as to form a strong classifier; and (e) effectuating pedestrian detection by searching the strong classifiers in thermal images with sliding window technique to detect for presence of pedestrians.

Abstract: A method of speeding up image detection, adapted to increase a speed of detecting a target image and enhance efficiency of image detection, comprises the steps of capturing an image; retrieving a plurality of characteristic points of the image; creating a region of interest (ROI) centered at the characteristic points each; creating a plurality of search point scan windows corresponding to the ROIs, respectively; calculating target hit scores of the characteristic points and the search point scan windows; comparing the target hit scores of the characteristic points and the search point scan windows to obtain an ROI most likely to have a target image; calculating centroid coordinates of the ROI by a centroid shift weight equation; and narrowing a scope of ROI search according to a location of the centroid coordinates and reducing a displacement between the search points.

Abstract: An all-weather thermal-image pedestrian detection method includes (a) capturing diurnal thermal images and nocturnal thermal images of a same pedestrian and non-pedestrian object in a same defined block to create a sample database of thermal images, wherein the sample database comprises pedestrian samples and non-pedestrian samples; (b) performing LBP encoding on the pedestrian samples and the non-pedestrian samples, wherein complementary LBP codes in the same defined block are treated as identical LBP codes; (c) expressing the LBP codes in the same defined block as features by a gradient direction histogram (HOG) to obtain feature training samples of the pedestrian samples and the non-pedestrian samples; (d) entering the feature training samples into a SVM to undergo training by Adaboost so as to form a strong classifier; and (e) effectuating pedestrian detection by searching the strong classifiers in thermal images with sliding window technique to detect for presence of pedestrians.

Abstract: A method of detecting temperature changes with infrared includes the steps of providing a plurality of infrared detection devices for detecting temperature changes in a region; turning on the plurality of infrared detection devices one by one at a first time interval; capturing temperature signals of the plurality of infrared detection devices one by one at a second time interval; and comparing the temperature signals with a background temperature signal to calculate temperature differences and thereby detect temperature changes in the region. A method of detecting moving vehicles with infrared is further introduced.

Abstract: A vehicle detection method includes (1) vehicle likelihood region identifying step; (2) vehicle component locating step; and (3) vehicle detecting step. To reduce complexity of calculation and enhance accuracy of detection, the method uses a vehicle likelihood region identifying algorithm to eliminate background regions from a total thermal image and keep vehicle likelihood regions therein for use in further analysis and processing, detects obvious vehicle components, such as vehicle windows and vehicle bottoms, in the thermal image to thereby identify vehicle component likelihood regions, describes a space geometric relationship of vehicle components with a Markov random field model, defines vehicle detection as problems with maximum a posteriori probability, estimates the most likely configuration with an optimization algorithm, so as to effectuate vehicle detection.

Abstract: A vehicle detection method includes (1) vehicle likelihood region identifying step; (2) vehicle component locating step; and (3) vehicle detecting step. To reduce complexity of calculation and enhance accuracy of detection, the method uses a vehicle likelihood region identifying algorithm to eliminate background regions from a total thermal image and keep vehicle likelihood regions therein for use in further analysis and processing, detects obvious vehicle components, such as vehicle windows and vehicle bottoms, in the thermal image to thereby identify vehicle component likelihood regions, describes a space geometric relationship of vehicle components with a Markov random field model, defines vehicle detection as problems with maximum a posteriori probability, estimates the most likely configuration with an optimization algorithm, so as to effectuate vehicle detection.

Abstract: An infrared logical matrix-style traffic violation detection method and apparatus are introduced for use at junctions of roads to detect traffic violations, such as going through a red light illegally and speeding, incur a low cost, and manifest a competitive edge. The apparatus includes a body, a sensing device, a signal determination processing device, an image capturing device, and a M×N array zone. The method includes the steps of starting a sensing device; detecting a M×N array zone; determining whether a temperature variation has occurred to the M×N array zone, and capturing a traffic violation-related image.

Abstract: A regulator includes a first amplifier, a second amplifier, a current control circuit, a first P-type metal-oxide-semiconductor transistor, a second P-type metal-oxide-semiconductor transistor, and a feedback circuit. The current control circuit includes a controller and at least one switch, and a second terminal of the first P-type metal-oxide-semiconductor transistor is coupled to a second terminal of the second P-type metal-oxide-semiconductor transistor. The regulator utilizes the controller to turn off the at least one switch during operation of the regulator in a light load mode, and the regulator utilizes the controller to turn on the at least one switch in turn when the regulator changes from the light load mode to a heavy load mode. Thus, the regulator can quickly recover a load current in the heavy load mode.

Abstract: A delay-locked loop includes a first delay unit, a second delay unit, a third delay unit, a phase detector, and a controller. The first delay unit generates a first delay clock according to a clock and a first delay time. The second delay unit generates a second delay clock according to the first delay clock and a second delay time. The third delay unit generates a third delay clock according to the second delay clock and a third delay time. The phase detector generates a phase detection signal according to the clock and the second delay clock. The controller generates and outputs a phase control signal according to the phase detection signal. The second delay unit and the third delay unit adjust the second delay time and the third delay time respectively according to the phase control signal.

Abstract: A delay-locked loop includes a first delay unit, a second delay unit, a third delay unit, a phase detector, and a controller. The first delay unit generates a first delay clock according to a clock and a first delay time. The second delay unit generates a second delay clock according to the first delay clock and a second delay time. The third delay unit generates a third delay clock according to the second delay clock and a third delay time. The phase detector generates a phase detection signal according to the clock and the second delay clock. The controller generates and outputs a phase control signal according to the phase detection signal. The second delay unit and the third delay unit adjust the second delay time and the third delay time respectively according to the phase control signal.