scispace - formally typeset
Search or ask a question
Topic

Detector

About: Detector is a research topic. Over the lifetime, 146515 publications have been published within this topic receiving 1351476 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: Calibration methods and software have been developed for single crystal diffraction experiments, using both approaches for calibrate, and apply corrections, to obtain accurate angle and intensity information.
Abstract: Detector systems introduce distortions into acquired data. To obtain accurate angle and intensity information, it is necessary to calibrate, and apply corrections. Intensity non-linearity, spatial distortion, and non-uniformity of intensity response, are the primary considerations. It is better to account for the distortions within scientific analysis software, but often it is more practical to correct the distortions to produce ‘idealised’ data. Calibration methods and software have been developed for single crystal diffraction experiments, using both approaches. For powder diffraction experiments the additional task of converting a two-dimensional image to a one-dimensional spectrum is used to allow Rietveld analysis. This task may be combined with distortion correction to produce intensity information and error estimates. High-pressure experiments can introduce additional complications and place new demands on software. Flexibility is needed to be able to integrate different angular regions se...

4,426 citations

Book ChapterDOI
07 May 2006
TL;DR: It is shown that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time.
Abstract: Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate. Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations [1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.

3,828 citations

Proceedings ArticleDOI
18 Jun 2018
TL;DR: Cascade R-CNN as mentioned in this paper proposes a multi-stage object detection architecture, which consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives.
Abstract: In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code is available at https://github.com/zhaoweicai/cascade-rcnn.

3,663 citations

Journal Article
TL;DR: In this paper, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations, and a comparison of corner detectors based on this criterion applied to 3D scenes is made.
Abstract: Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate. Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations[1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion. © Springer-Verlag Berlin Heidelberg 2006.

3,413 citations

Journal ArticleDOI
TL;DR: A snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions to establish a reference test set of images and performance software so that future detectors can be evaluated in the same framework.
Abstract: The paper gives a snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions. Six types of detectors are included: detectors based on affine normalization around Harris (Mikolajczyk and Schmid, 2002; Schaffalitzky and Zisserman, 2002) and Hessian points (Mikolajczyk and Schmid, 2002), a detector of `maximally stable extremal regions', proposed by Matas et al. (2002); an edge-based region detector (Tuytelaars and Van Gool, 1999) and a detector based on intensity extrema (Tuytelaars and Van Gool, 2000), and a detector of `salient regions', proposed by Kadir, Zisserman and Brady (2004). The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression. The objective of this paper is also to establish a reference test set of images and performance software, so that future detectors can be evaluated in the same framework.

3,359 citations


Network Information
Related Topics (5)
Monte Carlo method
95.9K papers, 2.1M citations
85% related
Scattering
152.3K papers, 3M citations
83% related
Image processing
229.9K papers, 3.5M citations
80% related
Optical fiber
167K papers, 1.8M citations
79% related
Spectroscopy
71.3K papers, 1.5M citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20234,093
20228,936
20212,560
20204,438
20195,208
20185,438