Results 1 -
9 of
9
Data-Driven 3D Voxel Patterns for Object Category Recognition
"... Despite the great progress achieved in recognizing ob-jects as 2D bounding boxes in images, it is still very chal-lenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Despite the great progress achieved in recognizing ob-jects as 2D bounding boxes in images, it is still very chal-lenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP), that jointly encodes the key properties of objects including appearance, 3D shape, viewpoint, occlu-sion and truncation. We discover 3DVPs in a data-driven way, and train a bank of specialized detectors for a dictio-nary of 3DVPs. The 3DVP detectors are capable of detect-ing objects with specific visibility patterns and transferring the meta-data from the 3DVPs to the detected objects, such as 2D segmentation mask, 3D pose as well as occlusion or truncation boundaries. The transferred meta-data allows us to infer the occlusion relationship among objects, which in turn provides improved object recognition results. Ex-periments are conducted on the KITTI detection benchmark [17] and the outdoor-scene dataset [41]. We improve state-of-the-art results on car detection and pose estimation with notable margins (6 % in difficult data of KITTI). We also verify the ability of our method in accurately segmenting objects from the background and localizing them in 3D. 1.
Fast and Robust Cyclist Detection for Monocular Camera Systems
"... Cyclist detection is an important task for automobile industries. In this pa-per we present a vision based system for cyclist detection. We build cascade detectors for cyclists in different viewpoints and part filters to deal with par-tial occlusions. To improve the performance, geometry based ROI e ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Cyclist detection is an important task for automobile industries. In this pa-per we present a vision based system for cyclist detection. We build cascade detectors for cyclists in different viewpoints and part filters to deal with par-tial occlusions. To improve the performance, geometry based ROI extraction method is integrated. Additionally, a Kalman filter in combination with optical flow is also applied to estimate cyclists ’ trajectories and to stabilize detections along image sequence. 1
An Exploration of Why and When Pedestrian Detection Fails
"... Abstract-This paper undergoes a finer-grained analysis of current state-of-the-art in pedestrian detection, with the aims of discovering insights into why and when detection fails. Current pedestrian detection research studies are often measured and compared by a single summarizing metric across da ..."
Abstract
- Add to MetaCart
Abstract-This paper undergoes a finer-grained analysis of current state-of-the-art in pedestrian detection, with the aims of discovering insights into why and when detection fails. Current pedestrian detection research studies are often measured and compared by a single summarizing metric across datasets. The progress in the field is measured by comparing the metric over the years for a given dataset. Nonetheless, this type of analysis may hinder development by ignoring the strengths and limitations of each method as well as the role of dataset-specific characteristics. For the experiments we employ two pedestrian detection datasets, Caltech and KITTI, and highlight their differences. The datasets are used in order to understand in what ways methods fail, and the impact of attributes, occlusion, and other challenges. Finally, the analysis is used to identify promising next steps for researchers.
Supplementary Material for “Data-Driven 3D Voxel Patterns for Object Category
"... We present the implementation details of our object cat-egory recognition framework and additional qualitative ex-amples on the KITTI dataset [5] and the OutdoorScene dataset [8] in this supplementary material. 1. Implementation Details ..."
Abstract
- Add to MetaCart
(Show Context)
We present the implementation details of our object cat-egory recognition framework and additional qualitative ex-amples on the KITTI dataset [5] and the OutdoorScene dataset [8] in this supplementary material. 1. Implementation Details
1Learning to Detect Objects at Multiple Orientations and Occlusion Levels
"... Abstract—We study efficient means of capturing intra-category diversity for object detection. Strategies for occlusion and ori-entation handling are explored by learning an ensemble of models using visual and geometrical features. An AdaBoost detection scheme is employed with pixel lookup features f ..."
Abstract
- Add to MetaCart
Abstract—We study efficient means of capturing intra-category diversity for object detection. Strategies for occlusion and ori-entation handling are explored by learning an ensemble of models using visual and geometrical features. An AdaBoost detection scheme is employed with pixel lookup features for achieving fast detection. The method show promise in terms of detection performance and orientation estimation accuracy on the challenging KITTI dataset. Index Terms—Object detection, multiorientation detection, mining appearance patterns, occlusion-handling, vehicle detec-tion, pedestrian detection, active safety, orientation estimation, performance evaluation. I.
Go with the flow: Improving Multi-View Vehicle Detection with Motion Cues
"... Abstract—As vehicles travel through a scene, changes in aspect ratio and appearance as observed from a camera (or an array of cameras) make vehicle detection a difficult computer vision problem. Rather than relying solely on appearance cues, we propose a framework for detecting vehicles and eliminat ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—As vehicles travel through a scene, changes in aspect ratio and appearance as observed from a camera (or an array of cameras) make vehicle detection a difficult computer vision problem. Rather than relying solely on appearance cues, we propose a framework for detecting vehicles and eliminating false positives by utilizing the motion cues in the scene in addition to the appearance cues. As a case study, we focus on overtaking vehicle detection in a freeway setting from forward and rear views of the ego-vehicle. The proposed integration occurs in two steps. First, motion-based vehicle detection is performed using optical flow. Taking advantage of epipolar constraints, salient motion vectors are extracted and clustered using spectral clustering to form bounding boxes of vehicle candidates. Post-processing and outlier removal further refine the detections. Second, the motion-based detections are then combined with the output of an appearance-based vehicle detector to reduce false positives and produce the final vehicle detections. I.
Traffic Sign Detection for U.S. Roads: Remaining Challenges and a case for Tracking
"... Abstract — Traffic sign detection is crucial in intelligent vehi-cles, no matter if one’s objective is to develop Advanced Driver Assistance Systems or autonomous cars. Recent advances in traffic sign detection, especially the great effort put into the competition German Traffic Sign Detection Bench ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract — Traffic sign detection is crucial in intelligent vehi-cles, no matter if one’s objective is to develop Advanced Driver Assistance Systems or autonomous cars. Recent advances in traffic sign detection, especially the great effort put into the competition German Traffic Sign Detection Benchmark, have given rise to very reliable detection systems when tested on European signs. The U.S., however, has a rather different approach to traffic sign design. This paper evaluates whether a current state-of-the-art traffic sign detector is useful for American signs. We find that for colorful, distinctively shaped signs, Integral Channel Features work well, but it fails on the large superclass of speed limit signs and similar designs. We also introduce an extension to the largest public dataset of American signs, the LISA Traffic Sign Dataset, and present an evaluation of tracking in the context of sign detection. We show that tracking essentially suppresses all false positives in our test set, and argue that in order to be useful for higher level analysis, any traffic sign detection system should contain tracking.
