Jeonghyun Baek

A Novel On-Road Vehicle Detection Method Using

In this paper, a new on-road vehicle detection method is presented. First, a new feature named the Position and Intensity-included Histogram of Oriented Gradients (PIHOG or πHOG) is proposed. Unlike the conventional HOG, πHOG compensates the information loss involved in the construction of a histogram with position information, and it improves the discriminative power using intensity information. Second, a new search space reduction (SSR) method is proposed to speed up the detection and reduce the computational load. The SSR additionally decreases the false positive rate. A variety of classifiers, including support vector machine, extreme learning machine, and k-nearest neighbor, are used to train and classify vehicles using πHOG. The validity of the proposed method is demonstrated by its application to Caltech, IR, Pittsburgh, and Kitti datasets. The experimental results demonstrate that the proposed vehicle detection method not only improves detection performance but also reduces computation time.

\pi

Simplified fuzzy ARTMAP (SFAM) is used in numerous classification problems due to its high discriminant power and low training time. However, the performance of SFAM is affected by the presentation order of the training patterns. The genetic algorithm (GA) can be considered as a solution to the problem because the selection of the training pattern order is a complicated combinatorial problem in a large search space. In this paper, a new genetic ordering method for SFAM is proposed to improve the performance of the algorithm. Special genetic operators are employed in the genetic evolution. Compared to the conventional methods, the proposed SFAM demonstrates better classification performance since it can efficiently deliver the desirable properties of parents to their offspring. To demonstrate the performance of the proposed method, we perform experiments on various databases from the UCI repository.

HOG

For reliable driving assistance or automated driving, pedestrian detection must be robust and performed in real time. In pedestrian detection, a linear support vector machine (linSVM) is popularly used as a classifier but exhibits degraded performance due to the multipostures of pedestrians. Kernel SVM (KSVM) could be a better choice for pedestrian detection, but it has a disadvantage in that it requires too much more computation than linSVM. In this paper, the cascade implementation of the additive KSVM (AKSVM) is proposed for the application of pedestrian detection. AKSVM avoids kernel expansion by using lookup tables, and it is implemented in cascade form, thereby speeding up pedestrian detection. The cascade implementation is trained by a genetic algorithm such that the computation time is minimized, whereas the detection accuracy is maximized. In experiments, the proposed method is tested with the INRIA dataset. The experimental results indicate that the proposed method has better detection accuracy and reduced computation time compared with conventional methods.

An efficient genetic selection of the presentation order in simplified fuzzy ARTMAP patterns

All kinds of vehicles have different ratios of width to height, which are called the aspect ratios. Most previous works, however, use a fixed aspect ratio for vehicle detection (VD). The use of a fixed vehicle aspect ratio for VD degrades the performance. Thus, the estimation of a vehicle aspect ratio is an important part of robust VD. Taking this idea into account, a new on-road vehicle detection system is proposed in this paper. The proposed method estimates the aspect ratio of the hypothesized windows to improve the VD performance. Our proposed method uses an Aggregate Channel Feature (ACF) and a support vector machine (SVM) to verify the hypothesized windows with the estimated aspect ratio. The contribution of this paper is threefold. First, the estimation of vehicle aspect ratio is inserted between the HG (hypothesis generation) and the HV (hypothesis verification). Second, a simple HG method named a signed horizontal edge map is proposed to speed up VD. Third, a new measure is proposed to represent the overlapping ratio between the ground truth and the detection results. This new measure is used to show that the proposed method is better than previous works in terms of robust VD. Finally, the Pittsburgh dataset is used to verify the performance of the proposed method.

Fast and Efficient Pedestrian Detection via the Cascade Implementation of an Additive Kernel Support Vector Machine

This paper proposes an effective hypothesis generation for detection multi-vehicle using a monocular camera fixed on the host vehicle. In hypothesis generation (HG) step, we use linear model between the distance and vehicle size by using recursive least square. It generates effective image patches and improves the detection performance. In addition, it also reduces the computation time compared with sliding-window approach. In hypothesis verification (HV) step, we use the Histogram of Oriented Gradient (HOG) feature and Support Vector Machine (SVM). In our experiment, Caltech and IR datasets are used. The experimental result shows the improvement of running time and detection performance.

New vehicle detection method with aspect ratio estimation for hypothesized windows

Hand posture classification has attracted much attention in Human-Computer Interaction (HCI). In hand posture classification, vision based approach is popularly used. However, it has difficulty of dealing with illumination change and pose variation. In this paper, we compare the performance of combination with features, which are HOG, LBP, and classifiers, which are SVM and Neural Network for hand posture classification. Experiments are performed with Cambridge hand gesture dataset.

On-road vehicle detection based on effective hypothesis generation

Most of the commercial nighttime pedestrian detection (PD) methods reported previously utilized the histogram of oriented gradient (HOG) or the local binary pattern (LBP) as the feature and the support vector machine (SVM) as the classifier using thermal camera images. In this paper, we propose a new feature called the thermal-position-intensity-histogram of oriented gradient (TPIHOG or TπHOG) and developed a new combination of the TπHOG and the additive kernel SVM (AKSVM) for efficient nighttime pedestrian detection. The proposed TπHOG includes detailed information on gradient location; therefore, it has more distinctive power than the HOG. The AKSVM performs better than the linear SVM in terms of detection performance, while it is much faster than other kernel SVMs. The combined TπHOG-AKSVM showed effective nighttime PD performance with fast computational time. The proposed method was experimentally tested with the KAIST pedestrian dataset and showed better performance compared with other conventional methods.

Comparison study of different feature classifiers for hand posture classification

An efficient pedestrian detection method is proposed for intelligent vehicles in this paper. The proposed method learns the region in which pedestrians are likely to be detected and narrows down the search to the likely region. The likely region is modeled as a Gaussian distribution on the y-axis and its parameters are updated by a Bayesian approach. Thus, the proposed method starts with an exhaustive full search, but gradually narrows down the search by focusing on the likely region. The learning of the likely region is formulated as a Bayesian learning problem and the likely region is analytically derived. The proposed method is combined with two popular pedestrian detection methods, Haar-like Adaboost and HOG-LSVM, and some experiments are conducted with the Caltech pedestrian dataset. The experiments show that the proposed method not only reduces computation time, but also enhances performance by rejecting false positive results.

Efficient pedestrian detection at nighttime using a thermal camera

Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representation method by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.

Bayesian learning of a search region for pedestrian detection

In this paper, we propose a new on-road vehicle detection system. Appearance of vehicles in image has various ratios because of its many kinds of models such as sedan, SUV and truck. For this reason, using ROI with fixed ratio can cause the degradation for detecting vehicles of various models. To solve this problem, we propose a new vehicle detection system using estimating ratio of vehicles. The proposed method estimates the ratio of vehicle ROI and extracted feature based evaluated ratio. It shows robust detection performance for various vehicle models because it extracts the feature from compact ROI with exact vehicle size. In our experiments, histogram of oriented histogram (HOG) feature and support vector machine (SVM) are used for the vehicle detection system. In order to evaluate the detection performance, the Pittsburgh dataset including various vehicle models such as sedan, SUV, truck and bus is used. In this dataset, it is shown that the proposed method is more robust than previous works to detect various vehicle models.