A new pedestrian recognition system based on edge detection and different census transform features under weather conditions

Abstract

<span lang="EN-US">Pedestrian detection has so far achieved great success in normal illumination, while pedestrians captured in extreme weather are often ignored. This paper investigates the importance of studying the effects of weather conditions on the recognition task, such as blurring and low contrast. Many image restoration techniques have recently been proposed, but are still insufficient to remove weather effects from images. We present our strong new pedestrian recognition system against climate situations, which is based on locating contours cues by applying multiple edge filters and extracting multiple features from images such as census transform (CT), modified census transform (MCT), and local gradient pattern (LGP) without performing any image restoration algorithm. The next stage involves finding the most discriminative characteristics using feature selection (FS) techniques. Finally, we use the final feature vector as an input to a radial basis function-based support vector machine classifier (RbfSVM) for pedestrian recognition. Experiments are performed on the daimler pedestrian classification benchmark dataset. Results show that the area under the curve (AUC) and the detection rate of our model are less affected by weather conditions compared to other common models like histogram of oriented gradients (HOG) and gabor filter bank (GFB) detectors.</span>

Facial recognition using multi edge detection and distance measure

“…Chen and Cheng [21], Razzok et al [22], Robert has explained that using a gradient operator with two 2×2 pixel matrices in (1). The process is to convolute grayscale images with Robert kernel matrix in horizontal (H) and vertical (V) directions, G is gradient pixels value; Gx is Robert horizontal gradient value; Gy is Robert vertical gradient value.…”

“…The Prewitt method involves convoluting grayscale images with Its matrix in horizontal (H) and vertical (V) directions. G is gradient value or pixel value (x, y); Gx is horizontal Prewitt gradient value; Gy is vertical Prewitt gradient value (4) [5], [21], [22].…”

“…The kernel above is a Gaussian kernel of order 5×5 with=1.4. Then, the magnitude of the gradient uses ( 14) below [5], [22]. The Canny kernel is convoluted with images, starting from the left row to the right side one pixel until it reaches the entire length horizontally.…”

“…The Euclidean distance (ED) method compares the minimum distance of the test image with the training image database [12], [22]. The ED of the two vectors x and y is calculated by (19) [23]:…”

Pedestrian detection system based on deep learning

“…Two of all useful information are the detection and location of pedestrians in front of a vehicle. Traditional object detection techniques in the past were based on are based on handcrafted features such as integral channel features (ICF) [1], [2], scale-invariant feature transform (SIFT) [3], histogram of oriented gradients (HOG) [4], local binary patterns (LBP) [5], general forward-backward (GFB) [6] ,and their variations [7]- [9] and combinations [10], [11], followed by a trainable classifier such as support vector machines (SVM) [7], [12], boosted classifiers [13], or random forests [14]. Their performance can be easily degraded by constructing complex ensembles that combine numerous low-level features with high-level context from object detectors and scene classifiers.…”