High Detection-rate Cascades for Real-Time Object Detection

Masnadi-Shirazi, Hamed; Vasconcelos, Nuno

doi:10.1109/iccv.2007.4408860

Cited by 20 publications

(19 citation statements)

References 10 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notable recent efforts for increasing detection speed include work by Felzenszwalb et al [44] and Pedersoli et al [45] on cascaded and coarseto-fine deformable part models, respectively, Lampert et al's [46] application of branch and bound search for detection, and Dollár et al's work on crosstalk cascades [40]. Cascades [27], [47], [48], [49], [50], coarse-to-fine search [51], distance transforms [52], etc., all focus on optimizing classification speed given precomputed image features. Our work focuses on fast feature pyramid construction and is thus complementary to such approaches.…”

Section: Related Workmentioning

confidence: 99%

Fast Feature Pyramids for Object Detection

Dollár

Appel

Belongie

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

1,819

1,156

View full text Add to dashboard Cite

Abstract-Multi-resolution image features may be approximated via extrapolation from nearby scales, rather than being computed explicitly. This fundamental insight allows us to design object detection algorithms that are as accurate, and considerably faster, than the state-of-the-art. The computational bottleneck of many modern detectors is the computation of features at every scale of a finelysampled image pyramid. Our key insight is that one may compute finely sampled feature pyramids at a fraction of the cost, without sacrificing performance: for a broad family of features we find that features computed at octave-spaced scale intervals are sufficient to approximate features on a finely-sampled pyramid. Extrapolation is inexpensive as compared to direct feature computation. As a result, our approximation yields considerable speedups with negligible loss in detection accuracy. We modify three diverse visual recognition systems to use fast feature pyramids and show results on both pedestrian detection (measured on the Caltech, INRIA, TUD-Brussels and ETH datasets) and general object detection (measured on the PASCAL VOC). The approach is general and is widely applicable to vision algorithms requiring fine-grained multi-scale analysis. Our approximation is valid for images with broad spectra (most natural images) and fails for images with narrow band-pass spectra (e.g. periodic textures).

show abstract

Section: Related Workmentioning

confidence: 99%

Fast Feature Pyramids for Object Detection

Dollár

Appel

Belongie

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

1,819

1,156

View full text Add to dashboard Cite

show abstract

“…A number of subsequent papers have addressed drawbacks of the original cascades [10][11][12]; however, perhaps the simplest and most elegant solution was proposed by Bourdev and Brandt in the form 'soft cascades' [8]. Instead of having multiple distinct cascade stages, a single boosted classifier is trained and only post-training are rejection thresholds set (with one threshold per weak classifier).…”

Section: Bounds On Soft Cascadesmentioning

confidence: 99%

“…Other related work can be broken down as follows. A significant body of work exists on optimizing cascades [7][8][9][10][11][12]; however, in all existing work each image window is evaluated independently. Research on fast feature extraction [7,13,4] is complementary to our own.…”

Section: Introductionmentioning

confidence: 99%

Crosstalk Cascades for Frame-Rate Pedestrian Detection

Dollár

Appel

Kienzle

2012

Lecture Notes in Computer Science

181

140

View full text Add to dashboard Cite

Abstract. Cascades help make sliding window object detection fast, nevertheless, computational demands remain prohibitive for numerous applications. Currently, evaluation of adjacent windows proceeds independently; this is suboptimal as detector responses at nearby locations and scales are correlated. We propose to exploit these correlations by tightly coupling detector evaluation of nearby windows. We introduce two opposing mechanisms: detector excitation of promising neighbors and inhibition of inferior neighbors. By enabling neighboring detectors to communicate, crosstalk cascades achieve major gains (4-30× speedup) over cascades evaluated independently at each image location. Combined with recent advances in fast multi-scale feature computation, for which we provide an optimized implementation, our approach runs at 35-65 fps on 640 × 480 images while attaining state-of-the-art accuracy.

show abstract

“…Most successful localization methods at the recent PASCAL VOC 2006 challenge [4] on object localization relied on this technique too, but these too still required a training phase. To make a real-time object detection system while achieving high detection rates, methods combining classifiers in a cascade [5], [6] have been proposed. Recently, the recognition task with only one query (training-free) has received increasing attention [7], [8], [9], [10] for important applications such as automatic passport control at airports, where a single photo in the passport is the only example available.…”

Section: Introductionmentioning

confidence: 99%

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

Seo

Milanfar

2010

IEEE Trans. Pattern Anal. Mach. Intell.

113

View full text Add to dashboard Cite

Abstract-We present a generic detection/localization algorithm capable of searching for a visual object of interest without training. The proposed method operates using a single example of an object of interest to find similar matches, does not require prior knowledge (learning) about objects being sought, and does not require any preprocessing step or segmentation of a target image. Our method is based on the computation of local regression kernels as descriptors from a query, which measure the likeness of a pixel to its surroundings. Salient features are extracted from said descriptors and compared against analogous features from the target image. This comparison is done using a matrix generalization of the cosine similarity measure. We illustrate optimality properties of the algorithm using a naive-Bayes framework. The algorithm yields a scalar resemblance map, indicating the likelihood of similarity between the query and all patches in the target image. By employing nonparametric significance tests and nonmaxima suppression, we detect the presence and location of objects similar to the given query. The approach is extended to account for large variations in scale and rotation. High performance is demonstrated on several challenging data sets, indicating successful detection of objects in diverse contexts and under different imaging conditions.

show abstract

High Detection-rate Cascades for Real-Time Object Detection

Abstract: Abstract

Cited by 20 publications

References 10 publications

Fast Feature Pyramids for Object Detection

Fast Feature Pyramids for Object Detection

Crosstalk Cascades for Frame-Rate Pedestrian Detection

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

Contact Info

Product

Resources

About