Rapid object detection using a boosted cascade of simple features
Citations
[...]
14,824 citations
[...]
14,747 citations
Cites methods from "Rapid object detection using a boos..."
...es of object detectors: those that use a sparse set of object proposals (e.g., selective search [21]) and those that use a dense set (e.g., DPM [8]). Classifying sparse proposals is a type of cascade [22] in which the proposal mechanism first rejects a vast number of candidates leaving the classifier with a small set to evaluate. This cascade improves detection accuracy when applied to DPM detections [2...
[...]
13,011 citations
Cites background from "Rapid object detection using a boos..."
...In order to make the paper more self-contained, we succinctly discuss the concept of integral images, as defined by [23]....
[...]
12,449 citations
Cites methods from "Rapid object detection using a boos..."
...This lends itself to the use of integral images as made popular by Viola and Jones [41], which reduces the computation time drastically....
[...]
12,161 citations
Cites background or methods from "Rapid object detection using a boos..."
...A common solution is to perform some form of hard negative mining [32, 36, 8, 30, 21] that samples hard examples during training or more complex sampling/reweighing schemes [2]....
[...]
...Class Imbalance: Both classic one-stage object detection methods, like boosted detectors [36, 5] and DPMs [8], and more recent methods, like SSD [21], face a large class imbalance during training....
[...]
...Viola and Jones [36] used boosted object detectors for face detection, leading to widespread adoption of such models....
[...]
...This inefficiency is a classic problem in object detection that is typically addressed via techniques such as bootstrapping [32, 28] or hard example mining [36, 8, 30]....
[...]
References
15,813 citations
10,525 citations
4,105 citations
"Rapid object detection using a boos..." refers methods or result in this paper
...Toward this end we have constructed a frontal face detection system which achieves detection and false positive rates which are equivalent to the best published results [14, 11, 13, 10, 1]....
[...]
...We tested our system on the MIT+CMU frontal face test set [11]....
[...]
...Evaluated on the MIT+CMU test set [11], an average of 10 features out of a total of 6061 are evaluated per sub-window....
[...]
...in which two detection networks are used [11]....
[...]
...For the Rowley-Baluja-Kanade results [11], a number of different versions of their detector were tested yielding a number of different results they are all listed in under the same heading....
[...]
3,365 citations
2,764 citations
"Rapid object detection using a boos..." refers background in this paper
...AdaBoost provides an effective learning algorithm and strong bounds on generalization performance [12, 8, 9]....
[...]