Introducing New AdaBoost Features for Real-Time Vehicle Detection
Bogdan Stanciulescu2009, Computing Research Repository
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
This paper shows how to improve the real-time object detection in complex robotics applications, by exploring new visual features as AdaBoost weak classifiers. These new features are symmetric Haar filters (enforcing global horizontal and vertical symmetry) and N-connexity control points. Experimental evaluation on a car database show that the latter appear to provide the best results for the vehicle-detection problem.
Related papers
Real-time visual detection of vehicles and pedestrians with new efficient adaBoost features
2008
This paper deals with real-time visual detection, by mono-camera, of objects categories such as cars and pedestrians. We report on improvements that can be obtained for this task, in complex applications such as advanced driving assistance systems, by using new visual features as adaBoost weak classifiers. These new features, the "connected controlpoints" have recently been shown to give very good results on real-time visual rear car detection. We here report on results obtained by applying these new features to a public lateral car images dataset, and a public pedestrian images database. We show that our new features consistently outperform previously published results on these databases, while still operating fast enough for real-time pedestrians and vehicles detection.
Adaboost with "Keypoint Presence Features" for Real-Time Vehicle Visual Detection
Computing Research Repository, 2009
We present promising results for real-time vehicle visual detection, obtained with adaBoost using new original "keypoints presence features". These weak-classifiers produce a boolean response based on presence or absence in the tested image of a "keypoint" (~ a SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as "wheel" or "side skirt") and thus have a "semantic" meaning.
Vehicle detection combining gradient analysis and adaboost classification
Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005., 2005
This paper presents a real-time vision-based vehicle detection system using gradient based methods and Adaboost classification. Our detection algorithm consists of two main steps : gradient driven hypothesis generation and appearance based hypothesis verification. In the hypothesis generation step, possible target locations are hypothesized. This step uses an adaptive range-dependant threshold and symmetry for gradient maxima localization. Appearance-based hypothesis validation verifies those hypothesis using AdaBoost for classification with illumination independent classifiers. The monocular system was tested under different traffic scenarios (e.g., simply structured highway, complex urban street, varying lightening conditions), illustrating good performance.
Moving Vehicle Detection Using Haar-like, LBP and a Machine Learning Adaboost Algorithm
Third IEEE International Conference on Image Processing, Applications and Systems (IPAS 2018), 2018
Object detection and classification is one of the core functions of Intelligence Transport Systems (ITS). It is typically based on extracted features and learning algorithms. Different approaches seem to be appropriate. Researchers should compare and evaluate existing approaches to apply the most efficient. In this paper, we propose a moving vehicle-detection vision system. Two solutions are examined in terms of performance and energy-efficient. The first is a classical Adaboost approach based on the Haar-like in feature extraction whereas the second handles a Local Binary Pattern descriptor that will undergo extraction with Adaboost classifier. Comparison results are illustrated based on the GTI vehicle image dataset. The most pertinent is the Haar-like +Adaboost, leading a DR of 90.1% instead of 87.9% for the LBP+Adaboost. However, LBP+Adaboost shows a low energy consumption, which is very important in any embedded systems.
Vehicle detection for autonomous parking using a Soft-Cascade AdaBoost classifier
2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014
This paper presents a monocular algorithm for front and rear vehicle detection, developed as part of the FP7 V-Charge project's perception system. The system is made of an AdaBoost classifier with Haar Features Decision Stump. It processes several virtual perspective images, obtained by unwarping 4 monocular fish-eye cameras mounted all-around an autonomous electric car. The target scenario is the automated valet parking, but the presented technique fits well in any general urban and highway environment. A great attention has been given to optimize the computational performance. The accuracy in the detection and a low computation costs are provided by combining a multiscale detection scheme with a Soft-Cascade classifier design. The algorithm runs in real time on the project's hardware platform.
A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection
EURASIP Journal on Advances in Signal Processing, 2008
We present an algorithm for the on-board vision vehicle detection problem using a cascade of boosted classifiers. Three families of features are compared: the rectangular filters (Haar-like features), the histograms of oriented gradient (HoG), and their combination (a concatenation of the two preceding features). A comparative study of the results of the generative (HoG features), discriminative (Haar-like features) detectors, and of their fusion is presented. These results show that the fusion combines the advantages of the other two detectors: generative classifiers eliminate "easily" negative examples in the early layers of the cascade, while in the later layers, the discriminative classifiers generate a fine decision boundary removing the negative examples near the vehicle model. The best algorithm achieves good performances on a test set containing some 500 vehicle images: the detection rate is about 94% and the false-alarm rate per image is 0.0003.
Rapid object detection using a boosted cascade of simple features. In: CVPR
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers[6]. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.
Visual object categorization with new keypoint-based adaBoost features
Computing Research Repository, 2009
We present promising results for visual object categorization, obtained with adaBoost using new original "keypoints-based features". These weak-classifiers produce a boolean response based on presence or absence in the tested image of a "keypoint" (a kind of SURF interest point) with a descriptor sufficiently similar (i.e. within a given distance) to a reference descriptor characterizing the feature. A first experiment was conducted on a public image dataset containing lateral-viewed cars, yielding 95% recall with 95% precision on test set. Preliminary tests on a small subset of a pedestrians database also gives promising 97% recall with 92 % precision, which shows the generality of our new family of features. Moreover, analysis of the positions of adaBoost-selected keypoints show that they correspond to a specific part of the object category (such as "wheel" or "side skirt" in the case of lateral-cars) and thus have a "semantic" meaning. We also made a first test on video for detecting vehicles from adaBoostselected keypoints filtered in real-time from all detected keypoints.
Haar-like features with optimally weighted rectangles for rapid object detection
Pattern Recognition, 2010
This article proposes an extension of Haar-like features for their use in rapid object detection systems. These features differ from the traditional ones in that their rectangles are assigned optimal weights so as to maximize their ability to discriminate objects from clutter (non-objects). These features maintain the simplicity of evaluation of the traditional formulation while being more discriminative. The proposed features were trained to detect two types of objects: human frontal faces and human heart regions. Our experimental results suggest that the object detectors based on the proposed features are more accurate and faster than the object detectors built with traditional Haar-like features.
Multiscaled Hybrid Features Generation for AdaBoost Object Detection
Journal of Medical Informatics and Technologies, 2015
This work presents the multiscaled version of modified census features in graphical objects detection with AdaBoost cascade training algorithm. Several experiments with face detector training process demonstrate better performance of such features over ordinal census and Haar-like approaches. The possibilities to join multiscaled census and Haar features in single hybrid cascade of strong classifiers are also elaborated and tested. The high resolution example images were used in detector training process.
Related topics
Related papers
Moving Vehicle Detection Using AdaBoost and Haar-Like Feature in Surveillance Videos
arXiv (Cornell University), 2018
Vehicle detection is a technology which its aim is to locate and show the vehicle size in digital images. In this technology, vehicles are detected in presence of other things like trees and buildings. It has an important role in many computer vision applications such as vehicle tracking, analyzing the traffic scene and efficient traffic management. In this paper, vehicles detected based on the boosting technique by Viola Jones. Our proposed system is tested in some real scenes of surveillance videos with different light conditions. The experimental results show that the accuracy, completeness, and quality of the proposed vehicle detection method are better than the previous techniques (about 94%, 92%, and 87%, respectively). Thus, our proposed approach is robust and efficient to detect vehicles in surveillance videos and their applications.
Robot Detection with a Cascade of Boosted Classifiers Based on Haar-Like Features
Lecture Notes in Computer Science, 2011
Accurate world modeling has great importance for efficient multirobot planning in robot soccer. Visual detection of the robots on the field in addition to all other objects of interest is crucial to achieve this goal. The problem of robot detection gets even harder when robots with only on board sensing capabilities, limited field of view, and restricted processing power are used. This work extends the real-time object detection framework proposed by Viola and Jones, and utilizes the unique chest and head patterns of Nao humanoid robots to detect them in the image. Experiments demonstrate rapid detection with an acceptably low false positive rate, which makes the method applicable for real-time use.
Vision-based pedestrian detection using Haar-like features
Proc. 6th National Festival of …, 2006
This paper describes a vision-based pedestrian detection system for robots, and autonomous vehicles. For that purpose the Haar-like features were used to discriminate pedestrians. Those features were used as input in a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields an extremely efficient classifier. The proposed system can run in real-time applications achieving good detection rates.
Autonomous Vehicle With Monocular Vision for Object Detection Using Haar-cascade Classifiers
2017
The biggest challenge in case of an autonomous driving system is proper integration of all the functions to be carried out for a safe driving experience. Detection of obstacles and prevention of collision plays an important role in road safety in case of such vehicles. The use of Haar-feature based cascade classifiers provides a light weight solution to object detection with extensive use of computer vision. With the help of monocular vision, image processing algorithms (Gaussian blur), identifying brightest spots (e.g. break lights of a car) and distance measuring algorithms, quick collision preventing actions can be taken. Multilayer Perceptron (MLP-ANN) can be used to classify objects and paths to create a simple decision making data structure for proper navigation. This paper illustrates on an intelligent self-driving vehicle that uses all the above methods tied together to drive on a predefined path. The monocular vision camera takes in image inputs that are processed and the a...
Cascade of Classifiers for Vehicle Detection
2007
Being aware of other vehicles on the road ahead is a key information to help driver assistance systems to increase driver’s safety. This paper addresses this problem, proposing a system to detect vehicles from the images provided by a single camera mounted in a mobile platform. A classifier–based approach is presented, based on the evaluation of a cascade of classifiers (COC) at different scanned image regions. The Adaboost algorithm is used to determine the COC from training sets. Two proposals are done to reduce the computation needed for the detection scheme used: a lazy evaluation of the COC, and the customization of the COC by a wrapping process. The benefits of these two proposals are quantified in terms of the average number of image features required to classify an image region, achieving a reduction of the 58% on this concept, while scarcely penalizing the detection accuracy of the system.
A new vehicle detection method
International Journal of Advanced Computer Science and Applications, 2011
This paper presents a new vehicle detection method from images acquired by cameras embedded in a moving vehicle. Given the sequence of images, the proposed algorithms should detect out all cars in realtime. Related to the driving direction, the cars can be classified into two types. Cars drive in the same direction as the intelligent vehicle (IV) and cars drive in the opposite direction. Due to the distinct features of these two types, we suggest to achieve this method in two main steps. The first one detects all obstacles from images using the so-called association combined with corner detector. The second step is applied to validate each vehicle using AdaBoost classifier. The new method has been applied to different images data and the experimental results validate the efficacy of our method.
Robust Real-time Object Detection
International Journal of Computer Vision, 2001
This paper describes a visual object detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features and yields extremely efficient classifiers . The third contribution is a method for combining classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. A set of experiments in the domain of face detection are presented. The system yields face detection performace comparable to the best previous systems . Implemented on a conventional desktop, face detection proceeds at 15 frames per second.
Selecting features for object detection using an AdaBoost-compatible evaluation function
Pattern Recognition Letters, 2008
This paper addresses the problem of selecting features in a visual object detection setup where a detection algorithm is applied to an input image represented by a set of features. The set of features to be employed in the test stage is prepared in two training-stage steps. In the first step, a feature extraction algorithm produces a (possibly large) initial set of features. In the second step, on which this paper focuses, the initial set is reduced using a selection procedure. The proposed selection procedure is based on a novel evaluation function that measures the utility of individual features for a certain detection task. Owing to its design, the evaluation function can be seamlessly embedded into an AdaBoost selection framework. The developed selection procedure is integrated with state-of-the-art feature extraction and object detection methods. The presented system was tested on five challenging detection setups. In three of them, a fairly high detection accuracy was effected by as few as six features selected out of several hundred initial candidates.
Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
ArXiv, 2021
A unified system integrating a compact object detector and a surrounding environmental condition classifier for enhancing the robustness of object detection scheme in advanced driver assistance systems (ADAS) is proposed in this paper. ADAS are invented to improve traffic safety and effectiveness in autonomous driving systems where the object detection plays an extremely important role. However, modern object detectors integrated in ADAS are still unstable due to high latency and the variation of the environmental contexts in the deployment phase. Our system is proposed to address the aforementioned problems. The proposed system includes two main components: (1) a compact one-stage object detector which is expected to be able to perform at a comparable accuracy compared to state-of-the-art object detectors, and (2) an environmental condition detector that helps to send a warning signal to the cloud in case the self-driving car needs human actions due to the significance of the situa...
Object Detection for Autonomous Driving
IRJET, 2022
The first ever production car came out in 1886 when Carl Benz applied for a patent for his vehicle which was powered by a gas engine. Ever since then the world has witnesses tremendous changes in the automotive sector. Earlier vehicles were handmade-some even to this datewhereas nowadays manufacturing is automated wherein vehicles are assembled through robots at the assembly line of the manufacturing plant. Technology has come a long way in order to develop intelligent transportation-to make transportation smart and effective. Some decades ago, who could have thought that one day cars will be able to drive themselves without an active driver, but self-driving technology has made this possible. The paper briefly discusses various object detection algorithms used nowadays which may be used in the backend of autonomous driving technology incorporated into these self-driving vehicles. The paper also discusses haar features, and the comparision of haar cascade classifier with YOLO V4 object detection algorithm with emphasis on specific use cases which is vehicle and pedestrian detection with varying accuracy.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.