Shin-Shinh Huang

Integrating Appearance and Edge Features for Sedan Vehicle Detection in the Blind-Spot Area

Changing lanes while having no information about the blind spot area can be dangerous. We propose a vision-based vehicle detection system for a lane changing assistance system to monitor the potential sedan vehicle in the blind-spot area. To serve our purpose, we select adequate features, which are directly obtained from vehicle images, to detect possible vehicles in the blind-spot area. This is challenging due to the significant change in the view angle of a vehicle along with its location throughout the blind-spot area. To cope with this problem, we propose a method to combine two kinds of part-based features that are related to the characteristics of the vehicle, and we build multiple models based on different viewpoints of a vehicle. The location information of each feature is incorporated to help construct the detector and estimate the reasonable position of the presence of the vehicle. The experiments show that our system is reliable in detecting various sedan vehicles in the blind-spot area.

Vision based obstacle warning system for on-road driving

Autonomous driving system can assist to prevent the traffic accidents caused by the negligence of the driver. Obstacle detection and warning mechanism plays an important role in this research field. In this paper, we adopt the computer vision technology because of its large detecting range and abundant information when compared to other kinds of sensors. The proposed system is suitable for both the simplified environment such as freeway and the urban environment with complex background. Thus, the result here improves traffic safety not only for drivers, but also for all pedestrians on the road.

Comparison of granules features for pedestrian detection

Pedestrian detection is an important part of intelligent transportation systems. In the literature, Histogram of Oriented Gradients (HOG) detector for pedestrian detection is known for its good performance, but there are still some false detections appearing in the cases with flat area or clustered background. To deal with these problems, in this research work we develop a new feature which is based on pairing comparison computations, called Comparison of Granules (CoG). The idea of CoG is to encode the textural information of local area describing how different the pixel intensities are distributed within a region. It is shown that the special characteristics of CoG feature are “small” and “efficiency” relative to HOG. By incorporating this new feature, we propose a HOG-CoG detector which through our validation experiment achieves 38% log-average miss rate in full image evaluation and 90% detection rate at 10-4 false positives per window on INRIA Person Dataset. Another contribution of this work is that, we also present a training scheme that can be applied on huge database for training a detector. Such training scheme can reduce the number of hard samples during bootstrap training.

Incorporating appearance and edge features for vehicle detection in the blind-spot area

It is dangerous that changing lane without knowing the information of the other lane in the blind-spot area. We propose a vision based lane changing assistance system to monitor the vehicle in the blind-spot area. So far in the literature, only few results are found using the features of the vehicle to detect the vehicle. Without using features from vehicle, to conclude that vehicles do appear in that area with strong evidence is hard. We use the image features which are directly obtained from vehicle images to detect vehicles possibility in the area. In order to overcome large variation problem due to significant difference in view angle during the process of detecting vehicles in the blind-spot area, we propose a method to combine two kinds of part-based features. After building all the features from training images, we use Adaboost algorithm to choose the best features with better geometric information for detection. The experiments show that our system is reliably in detecting the vehicles in the blind-spot area.

On-road computer vision based obstacle detection

Applying computer technology to vehicle driving has been studied for many years. In this research field, obstacle detection plays an important role in assisting drivers with warning mechanism when some dangerous situations may happen. In this paper, we propose a fast method for detecting and tracking bikes, pedestrians, and vehicles in front of a moving vehicle. In order to detect bikes and pedestrians efficiently, we apply a simplified fast stereo vision method to estimate their approximate positions. On the other hand, we apply the so-called sign pattern technique to estimate the vehicle positions. After that, different methods are used to classify and confirm different kinds of obstacles for adapting their heterogeneity.

Combining multiple complementary features for pedestrian and motorbike detection

Pedestrian and motorbike detection are two important areas in obstacle detection on road. Most state-of-the-art detectors are constructed with new features or learning methods on Histograms of Oriented Gradients (HOG) features. However, few researches focus on analyzing which features are complementary for the aforementioned detection. According to our study of pedestrians and motorbikes, there are three major properties including shape, texture, and self-similarity. We design a Shape, Texture and Self-Similarity (STSS) feature for these properties. The features we have employed here are HOG, Local Oriented Pattern (LOP), Color Self-Similarity (CSS), and Texture Self-Similarity (TSS). The STSS detector which combines Shape, Texture, and Self-Similarty features achieves 31% log-average miss rate. At the same time, 93% detection rate at 10-4 false positives per window on INRIA Person Dataset has also been concluded. Besides, we also have evaluated our detector on Caltech Motorbike Dataset and Caltech Pedestrian Dataset, and found the detector outperforms HOG detector in these datasets. As a result, we have shown that these features are complement to each other and useful in pedestrian and motorbike detection.

Tracking and detection of lane and vehicle integrating lane and vehicle information using PDAF tracking model

We propose a robust system for multi-vehicle and multi-lane detection with integrating lane and vehicle information. Most research work only can detect the lanes or vehicles separately. However, the dependency between lane information and vehicle information are able to support each other achieving more reliable results. We use probabilistic data association filter to integrate the information of lane and vehicle. In probabilistic data association filter, cumulate history of target is kept in the data association probability. Target tracking can improve the detection results through region of interests. At the same time, a high-level traffic model combines the lane and vehicle information. The tracking and detection can benefit each other through iterations. Experimental results show that our approach can detect multi-vehicle and multi-lane reliably.

Pedestrian and Vehicle Detection and Tracking with Object-Driven Vanishing Line Estimation

To robustly detect people and vehicle on the road in a video sequence is a challenging problem. Most researches focus on detecting or tracking of specific targets only. On the contrary, instead of detecting vehicle or pedestrian individually, an integration framework combining the geometric information is proposed. The camera’s pitch angle is estimated with a novel vanishing line estimator. Not only detecting the vanishing point using line intersection approach, but also the object information from tracker are considered. Specifically, the detected vehicle or pedestrian will cast votes for the hypothesized horizon line. The vanishing line can be estimated even when the scenes are cluttered or crowded, and thus the geometric information can be estimated under challenging circumstance. In turn, such information of scene can help the system refine our detection results through Bayes’ network. Finally, to verify the performance of the system, comprehensive experiments have been conducted with the KITTI dataset. It is quite promising that the state-of-the-art detector, in our case, Regionlet detector, can be improved.