3D Scene priors for road detection
Citations
608 citations
Cites background or methods from "3D Scene priors for road detection"
...Consequently, many approaches put higher emphasis on appearance cues such as the color and texture of the road area [5], [6], [7], [8], [9], [10], [11], [12]....
[...]
...These visual properties of the road area have been used for estimating the overall road shape [12] or for segmenting the complete road area [5], [6], [8], [10]....
[...]
...Metrics include the classical true positive (TP) and false positive (FP) rates on the pixel/patch level [20], [21], [22], the accuracy [6] as well as precision/recall and the derived F-measure [7], [10], [18]....
[...]
...Similar to [7], [10], [18], we employ the F-measure derived from the precision and recall values (Eq....
[...]
...These baselines can be viewed as scene priors similar to the one used as input to [10]....
[...]
579 citations
Additional excerpts
...Alvarez et al. (2010) propose a Bayesian framework to clas-...
[...]
453 citations
114 citations
83 citations
References
7,660 citations
"3D Scene priors for road detection" refers methods in this paper
...To this end, an exponentially weighted moving average (EWMA) [20, 21] is used to express the dynamic structure of the data (previously detected road)....
[...]
...EWMA uses a decay factor that weighs the influence of each past result....
[...]
...Further, EWMA assumes that the road detected in the current frame is correlated (similar) to the road detected in previous frames....
[...]
...Using EWMA, the weights are computed as follows: E[p(xi = R)t ] = 1 ∑Tj=1 λ j−1 T ∑ j=1 λ j−1 p(xi = R)(t− j), (1) where E[p(xi = R)t ] is the expected probability of a pixel being a road at discrete instant time t (current frame) and p(xi = R)(t− j) is the probability of a pixel being a road j frames before the frame being analyzed....
[...]
6,882 citations
"3D Scene priors for road detection" refers methods in this paper
...This method estimates the horizon line by applying non–linear mixtures of linear regressors to the description of an image obtained using gist descriptors [13]....
[...]
5,670 citations
Additional excerpts
...In general, combining multiple classifiers is a powerful technique to improve the performance of single classifiers [9, 7]....
[...]
3,933 citations
"3D Scene priors for road detection" refers methods in this paper
...Finally, the proposed method provides highest road detection accuracy when compared to state–of–the–art methods....
[...]
3,920 citations
"3D Scene priors for road detection" refers methods in this paper
...Following the approach in [16], images are described using opponent SIFT descriptor with dense sampling [17] (10 pixels sampling grid)....
[...]