Design of pedestrian detectors using combinations of scale spaces and classifiers (original) (raw)
Related papers
A pedestrian detector using histograms of oriented gradients and a Support Vector Machine classifier
IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2007
This paper details filtering subsystem for a tetravision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. This list is furtherly refined using symmetry-based assumptions. Then, this results is fed to a number of independent validators that evaluate the presence of human shapes inside the areas of attention.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2021
This paper proposes a scale-invariant histogram of oriented gradients (SI-HOG) for pedestrian detection. Most of the algorithms for pedestrian detection use the HOG as the basic feature and combine other features with the HOG to form the feature set, which is usually applied with a support vector machine (SVM). Hence, the HOG feature is the most efficient and fundamental feature for pedestrian detection. However, the HOG feature produces feature vectors of different lengths for different image resolutions; thus, the feature vectors are incomparable for the SVM. The proposed method forms a scale-space pyramid wherein the histogram bin is calculated. Thus, the gradient information from all the scales is encapsulated in a single fixed-length feature vector. The proposed method is also combined with color and texture features. The proposed approach is tested on three established benchmark pedestrian datasets: INRIA, NICTA, and Daimler. An improvement of ≥ 4.5% in the miss rate is achieved for all the three datasets considered. We also show that the SI-HOG can be applied to multiresolution datasets for which the HOG feature cannot be applied. Additionally, the MapReduce model is used to obtain the same outcome. The results indicate that the proposed approach outperforms the pedestrian-detection methods considered in this work.
Detecting pedestrians on a Movement Feature Space
Pattern Recognition, 2014
This work aims at detecting pedestrians in surveillance video sequences. A pre-processing step detects motion regions on the image using a scene background model based on level lines, which generates a Movement Feature Space, and a family of oriented histogram descriptors. A cascade of boosted classifiers generates pedestrian hypotheses using this feature space. Then, a linear Support Vector Machine validates the hypotheses that are likeliest to contain a person. The combination of the three detection phases reduces false positives, preserving the majority of pedestrians. The system tests conducted in our dataset, which contains low-resolution pedestrians, achieved a maximum performance of 25.5 % miss rate with a rate of of 10 −1 false positives per image. This value is comparable to the best detection values for this kind of images. In addition, the processing time is between 2 and 6 fps on 640x480 pixel captures. This is therefore a fast and reliable pedestrian detector.
2021
Various researches have been conducted over vision based pedestrian detection techniques for smart vehicles. In fact, it is one of the booming research topics, how a system can be developed such that a moving vehicle can detect a pedestrian in a potential hit region and warns the driver of the situation or automatically reacts to the situation by slowing down the speed. To achieve this, it falls back to the basic problem of how the pedestrian can be detected in the initial stage. Although this vision-based pedestrian detection process could be divided into three consecutive steps: pedestrian detection, pedestrian recognition and pedestrian tracking. In this paper, we deal with pedestrian detection in detail using pre-trained HOG + Linear SVM model in OpenCV and the future prospects of the research.
Fast pedestrian detection with multi-scale orientation features and two-stage classifiers
2010
In this paper, we propose an approach for fast pedestrian detection in images. Inspired by the histogram of oriented gradient (HOG) features, a set of multi-scale orientation (MSO) features are proposed as the feature representation. The features are extracted on square image blocks of various sizes (called units), containing coarse and fine features in which coarse ones are the unit orientations and fine ones are the pixel orientation histograms of the unit. A cascade of Adaboost is employed to train classifiers on the coarse features, aiming to high detection speed. A greedy searching algorithm is employed to select fine features, which are input into SVMs to train the fine classifiers, aiming to high detection accuracy. Experiments report that our approach obtains state-of-art results with 12.4 times faster than the SVM+HOG method.
Pedestrian Detection using Linear SVM Classifier with HOG Features
2018
Detecting pedestrians in an image is a useful technique in the development of the Intelligent Transportation System (ITS). Histogram of Oriented Gradient (HOG) is widely used as a feature algorithm and treated the entire body of the human as a single feature. In this paper, we compared the well-known feature based approaches: Haar features and HOG features in PSU pedestrian dataset under complex backgrounds, wide illuminations, large variation on pose and clothing. In practice, there are many complex movements and backgrounds in the real world environments. The experiment results show that a rich feature set supports the better detection performance. The performance of the detection results show that the accuracy of the HOG training model is 45.93% which is much better than Haar training model. Our proposed method can also apply to detect human in the real-world environment.
Towards Practical Evaluation of Pedestrian Detectors
2008
Despite recent significant advancement in the area of pedestrian detection in images, little effort has been devoted to algorithm evaluation for practical purposes. Typically, detectors are evaluated only on color images. It is not clear how the performance would be affected if other modalities are used, e.g. thermal or near infrared. Also, detectors are evaluated on cropped images that have the same size as training images. However, in practice, detectors are applied to large images with multiple pedestrians in different locations and sizes. To apply a single size pedestrian detector, the input image is, typically, scanned several times with different window sizes. It is not clear how the detection performance would be affected by such multiple-size scanning technique. Moreover, to implement such a technique, one is faced with a multitude of design choices, each of which potentially affects the performance of the detector. The contribution of this paper is to assess and reason about the differences in detection performance of two state of the art detectors across changes in modality (visible or near infrared), evaluation method (on cropped or whole images), the effect of different design choices (resizing features or images, smoothing or not).
Selection of Histograms of Oriented Gradients Features for Pedestrian Detection
Lecture Notes in Computer Science, 2008
Histograms of Oriented Gradients (HOG) is one of the wellknown features for object recognition. HOG features are calculated by taking orientation histograms of edge intensity in a local region. N.Dalal et al. proposed an object detection algorithm in which HOG features were extracted from all locations of a dense grid on a image region and the combined features are classified by using linear Support Vector Machine (SVM). In this paper, we employ HOG features extracted from all locations of a grid on the image as candidates of the feature vectors. Principal Component Analysis (PCA) is applied to these HOG feature vectors to obtain the score (PCA-HOG) vectors. Then a proper subset of PCA-HOG feature vectors is selected by using Stepwise Forward Selection (SFS) algorithm or Stepwise Backward Selection (SBS) algorithm to improve the generalization performance. The selected PCA-HOG feature vectors are used as an input of linear SVM to classify the given input into pedestrian/non-pedestrian. The improvement of the recognition rates are confirmed through experiments using MIT pedestrian dataset.
Real-time Pedestrian Detection in Urban Scenarios
IEEE 10th International Conference on Intelligent Computer Communication and Processing (ICCP), 2014
A real-time pedestrian detection system is presented that runs at 24 fps on standard VGA resolution input images (640x480px) using only CPU processing. The detection algorithm uses a variable sized sliding window and intelligent simplifications such as a sparse scale space and fast candidate selection to obtain the desired speed. Details are provided about the initial version of the system ported on a mobile device. We also present a new labeled pedestrian dataset that was captured from a moving car that is suitable for training and testing pedestrian detection methods in urban scenarios.
A Survey of Pedestrian Detection in Video
Pedestrian detection is one of the important topics in computer vision with key applications in various fields of human life such as intelligent vehicles, surveillance and advanced robotics. In recent years, research related to pedestrian detection commonplace. This paper aims to review the papers related to pedestrian detection in order to provide an overview of the recent research. Main contribution of this paper is to provide a general overview of pedestrian detection process that is viewed from different sides of the discussion. We divide the discussion into three stages: input, process and output. This paper does not make a selection or technique best method and optimal because the best technique depends on the needs, concerns and existing environment. However, this paper is useful for future researchers who want to know the current researches related to pedestrian detection.