Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis
Citations
486 citations
460 citations
434 citations
Cites background from "Looking at Vehicles on the Road: A ..."
...For more information on conventional hand-crafted feature/cue based approaches, interested readers may refer to the following survey papers: [68,69] for lane line marking detection, [70] for road surface detection, [71,72] for vehicle detection and [73] for pedestrian detection....
[...]
403 citations
Cites background from "Looking at Vehicles on the Road: A ..."
...Such configuration uses matching algorithms to find correspondences in both images and calculate the depth of each point relative to the camera, demanding more processing power [18]....
[...]
364 citations
References
37,861 citations
"Looking at Vehicles on the Road: A ..." refers background in this paper
...Discriminative classifiers, which learn a decision boundary between two classes, have been more widely used in vehicle detection....
[...]
31,952 citations
"Looking at Vehicles on the Road: A ..." refers methods in this paper
...The tracking problem is formulated as a maximum a posteriori inference problem over a random Markov field....
[...]
...Symmetry and edges were also used in [32] and [33], with longitudinal distance and time to collision (TTC) estimated using assumptions on the 3-...
[...]
23,396 citations
"Looking at Vehicles on the Road: A ..." refers background or methods in this paper
...In [3], Kalman filtering is used to estimate the vehicles’ yaw rate, as well as position and velocity....
[...]
...D ranging and for estimating the ground plane....
[...]
...Candidate vehicles’ locations were predicted using Kalman filtering in the image plane....
[...]
18,620 citations
"Looking at Vehicles on the Road: A ..." refers background or methods in this paper
...Haar-like features have been extensively used to detect the rear faces of preceding vehicles, using a forward-facing camera [37], [41]– [49]....
[...]
...Symmetry and edges were also used in [32] and [33], with longitudinal distance and time to collision (TTC) estimated using assumptions on the 3-...
[...]
...HOG features are descriptive image features, exhibiting good detection performance in a variety of computer vision tasks, including vehicle detection, but they are generally slow to compute....
[...]