Integral Histogram with Random Projection for Pedestrian Detection
نویسندگان
چکیده
In this paper, we give a systematic study to report several deep insights into the HOG, one of the most widely used features in the modern computer vision and image processing applications. We first show that, its magnitudes of gradient can be randomly projected with random matrix. To handle over-fitting, an integral histogram based on the differences of randomly selected blocks is proposed. The experiments show that both the random projection and integral histogram outperform the HOG feature obviously. Finally, the two ideas are combined into a new descriptor termed IHRP, which outperforms the HOG feature with less dimensions and higher speed.
منابع مشابه
Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates
In this paper, we present a new pedestrian detection method combining Random Forest and Dominant Orientation Templates(DOT) to achieve state-of-the-art accuracy and, more importantly, to accelerate run-time speed. DOT can be considered as a binary version of Histogram of Oriented Gradients(HOG) and therefore provides time-efficient properties. However, since discarding magnitude information, it...
متن کاملPedestrian Detection and Tracking in Images and Videos
The increase in population density and accessibility to cars over the past decade has led to extensive computer vision research in recognition and detection to promote a safer environment. Primarily, much of the research focuses on detecting pedestrians in order to reduce the chance of collision, and to improve traffic control. The need for increased surveillance at the work place and at home a...
متن کاملStreet crossing pedestrian detection based on edge curves motion
This paper presents a real-time method for detecting pedestrians using vertical motion form two consecutives frames. We used association approach to match edge curves between consecutive images. Significant motions can be found using horizontal-vertical projection histogram. Then the pedestrian detection process is achieved in two steps. The first one searches the region of interest by using th...
متن کاملA Cascade of Feed-Forward Classifiers for Fast Pedestrian Detection
We develop a method that can detect humans in a single image based on a new cascaded structure. In our approach, both the rectangle features and 1-D edge-orientation features are employed in the feature pool for weak-learner selection, which can be computed via the integral-image and the integral-histogram techniques, respectively. To make the weak learner more discriminative, Real AdaBoost is ...
متن کاملPedestrian Detection by Using a Spatio-Temporal Histogram of Oriented Gradients
In this paper, we propose a pedestrian detection algorithm based on both appearance and motion features to achieve high detection accuracy when applied to complex scenes. Here, a pedestrian’s appearance is described by a histogram of oriented spatial gradients, and his/her motion is represented by another histogram of temporal gradients computed from successive frames. Since pedestrians typical...
متن کامل