USRE42999E1 - Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology - Google Patents
Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology Download PDFInfo
- Publication number
- USRE42999E1 USRE42999E1 US11/645,331 US64533106A USRE42999E US RE42999 E1 USRE42999 E1 US RE42999E1 US 64533106 A US64533106 A US 64533106A US RE42999 E USRE42999 E US RE42999E
- Authority
- US
- United States
- Prior art keywords
- scene
- self
- inference process
- consistency
- statistical analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Lifetime, expires
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
Definitions
- the present invention relates to the field of inference algorithms.
- An inference algorithm is any algorithm that takes input observations from the world and makes inferences about the causes of those observations.
- Different types of inference algorithms are stereo algorithms and computer vision algorithms.
- Inference algorithms are used in several areas including three-dimensional imaging and voice recognition and natural language understanding. As technology utilizing inference algorithms advances, methods for determining the accuracy of these algorithms is essential. Accuracy determinations are based on statistical characterizations of the performance of the algorithm.
- ground truth One possible statistical characterization of the performance of an inference algorithm is in terms of the error of the matches compared to “ground truth.” Comparison with ground truth requires the build up a corpus of ground truth observations and training the algorithm based on the corpus. If sufficient quantities of ground truth are available estimating the distribution of errors over many image pairs of many scenes is relatively straight forward. This distribution could then be used as a prediction of the accuracy of matches in new images.
- ground truth has several drawbacks. Acquiring ground truth for any scene is an expensive and problematic proposition, as several observations must be recorded. Also, aquiring ground truth for any scene is extremely time and labor intensive. Furthermore, any ground truth measurements are subject to discrepancies in the measurements, therefore reducing the accuracy of the performance.
- the present invention provides a method for measuring the self-consistency of inference algorithms.
- the present invention provides a method for measuring the accuracy of an inference algorithm that does not require comparison to ground truth. Rather, the present invention pertains to a method for measuring the accuracy of an inference algorithm by comparing the outputs of the inference algorithm against each other. Essentially, the present invention looks at how well the algorithm applied to many of the different observations gives the same answer. In particular, the present invention provides a method that is not time and labor intensive and is cost effective.
- the present invention pertains to a method for estimating the accuracy of inference algorithms using self-consistency methodology.
- Self-consistency methodology relies on the outputs of an inference algorithm independently applied to different sets of views of a static scene to estimate the accuracy of every element of the output of the algorithm for a given set of views.
- An algorithm consistent across many different observations of the same thing is a self-consistent algorithm.
- self-consistency methodology the output is compared against itself over many different observations.
- An algorithm is self-consistent where it gives the same answer when applied to many observations.
- the algorithm is applied to many different observations of the same static scene.
- the observations are then compared to each other in a manner that is a function of the exact nature of the observation and the inferences made.
- a statistical analysis of the self-consistency is then made which is used to fine-tune an algorithm or compare different algorithms.
- the internal parameters of the algorithm are adjusted after each comparison to make the inference algorithm more and more consistent. This is useful for fine-tuning an algorithm to increase its effectiveness and accuracy.
- different inference algorithms may be compared against each other over a number of observations. This is useful for determining whether one algorithm is more effective or accurate than another algorithm. This is also useful for determining when one algorithm is better than another algorithm.
- FIG. 1 is a perspective view of a common-point match set.
- FIG. 2(a) illustrates a sample scene of an aerial view of terrain.
- FIG. 2(b) illustrates a sample scene of an aerial view of a tree canopy.
- FIG. 2(c) is a graphical representation of a self-consistency distribution for an image of an aerial view of terrain.
- FIG. 2(d) is a graphical representation of a self-consistency distribution for an image of an aerial view of a tree canopy.
- FIG. 2(e) is a graphical representation of a score dependent scatter diagram for an image of an aerial view of terrain.
- FIG. 2(f) is a graphical representation of a score dependent scatter diagram for an image of an aerial view of a tree canopy.
- FIG. 3 illustrates six graphical representations of simulations comparing un-normalized versus normalized self-consistency distributions.
- FIG. 4 illustrates two graphical representations of simulations comparing averaged theoretical and experimental curves.
- FIG. 5 illustrates a graphical representation of the merged distributions for a deformable mesh algorithm and a stereo algorithm.
- FIG. 6 illustrates three graphical representations of scatter diagrams for different scores.
- FIG. 7 illustrates three depictions of urban scenes.
- FIG. 8(a) illustrates three graphical representations of the combined self-consistency distributions of six urban scenes.
- FIG. 8(b) illustrates three graphical representations of the scatter diagrams for the MDL score of six urban scenes.
- FIG. 9(a) illustrates one images of a scene at time t 1
- FIG. 9(b) illustrates one images of a scene at time t 2 .
- FIG. 9(c) shows all significant differences found between all pairs of images at times t 1 and t 2 for a window size of 29 ⁇ 29 (applied to a central region of the images).
- FIG. 9(d) shows the union of all significant differences found between matches derived from all pairs of images taken at time t 1 and all pairs of images taken at time t 2 .
- FIG. 10 is a flowchart showing the steps in a process for estimating the accuracy of inference algorithms using self-consistency methodology.
- FIG. 11(a) illustrates a scatter diagram for 170 image pairs of rural scenes.
- FIG. 11(b) illustrates a histogram of the normalized difference in the z coordinate of the triangulation of all common-xy-coordinate match pairs.
- FIG. 12(a) illustrates a graphical representation of a scatter diagram.
- FIG. 12(b) illustrates a graphical representation of a histogram.
- FIG. 13(a) illustrates one of 5 images of a scene taken in 1995.
- FIG. 13(b) illustrates one of 5 images of a scene taken in 1998.
- FIG. 13(c) illustrates an image where vertices that were deemed to be significantly are overlaid as white cross on the image in which is a magnified view of the dried creek bed of FIG. 13(a) .
- FIG. 14(a) illustrates a graphical representation of a scatter diagram.
- FIG. 14(b) illustrates a graphical representation of a histogram.
- FIG. 15(a) illustrates a graphical representation of a scatter diagram.
- FIG. 15(b) illustrates a graphical representation of a histogram.
- FIG. 16(a) shows one of 4 images taken at time 1
- FIG. 16(b) shows one of the images taken at time 2 .
- FIG. 16(c) shows the significant differences between the matches derived from a single pair of images taken at time 1 and the matches derived from a single pair of images taken at time 2 .
- FIG. 16(d) shows the merger of the significant differences between each pair of images at time 1 and each pair of images at time 2 .
- FIG. 17(a) shows the differences between a single pair of images at time 1 and a single pair of images at time 2 , for a threshold of 3 units.
- FIG. 17(b) shows the differences for a threshold of 6 units, which is the average difference detected in FIG. 14 .
- FIG. 17(c) illustrates the union of the differences for all image pairs.
- FIG. 18 illustrates the results of change detection an urban scene with a new building.
- FIG. 19 illustrates the results of change detection for an urban scene without significant changes.
- FIG. 20 is a block diagram of an exemplary computer system in accordance with one embodiment of the present invention.
- FIG. 21 is a flowchart showing the steps in a process for detecting changes in the 3-D shape of terrain and/or buildings from aerial or satellite images using self-consistency methodology.
- a new approach to characterizing the performance of point-correspondence algorithms by automatically estimating the reliability of hypotheses (inferred from observations of a “scene”) by certain classes of algorithms is presented.
- scene refers not only to visual scenes, but to the generic scene. (e.g. anything that so can be observed—audio observations for voice recognition purposes).
- An example is an algorithm that infers the 3-D shape of an object (i.e., a collection of hypotheses about the world) from a stereo image pair (the observation of the scene).
- any “ground truth” it uses the self-consistency of the outputs of an algorithm independently applied to different sets of views of a static scene. It allows one to evaluate algorithms for a given class of scenes, as well as to estimate the accuracy of every element of the output of the algorithm for a given set of views. Experiments to demonstrate the usefulness of the methodology are presented.
- the human visual system exhibits the property of self-consistency: given a static natural scene, the perceptual inferences made from one viewpoint are almost always consistent with the inferences made from a different viewpoint.
- the first step towards the goal of designing self-consistent computer vision algorithms is to measure the self-consistency of the influences of the current computer vision algorithm over many scenes. An important refinement of this is to measure the self-consistency of subsets of an algorithm's inferences that satisfy certain measurable criteria, such as having “high confidence.”
- self-consistency is a necessary, but not sufficient, condition for a computer vision algorithm to be correct. That is, it is possible (in principle) for a computer vision algorithm to be self-consistent over many scenes but be severely biased or entirely wrong. It is conjectured that this cannot be the case for non-trivial algorithms. If bias can be ruled out, then the self-consistency distribution becomes a measure of the accuracy of an algorithm—one which requires no “ground truth.” Also, self-consistency must be measured over a wide variety of scenes to be a useful predictor of self-consistency over new scenes. In practice, one can measure self-consistency over certain classes of scenes, such as close-up views of faces or aerial images of natural terrain.
- An observation ⁇ is one or more images of the world taken at the same time, perhaps accompanied by meta-data, such as the time the image(s) was acquired, the internal and external camera parameters, and their covariances. It should be appreciated that this example is applicable to observations other than images, but also to anything that can be observed (e.g. audio observations for voice recognition purposes).
- a hypothesis h nominally refers to some aspect or element of the world (as opposed to some aspect of the observation), and it normally estimates some attribute of the element it refers to. This is formalized with the following set of functions that depend both on F and ⁇ :
- the second term on the right is the Mahalanobis distance between the attributes which is referred to as the normalized distance between attributes.
- This distribution of C(h, h′) is called the self-consistency distribution of the computer vision algorithm F over the worlds W.
- the distribution for only pairs h and h′ are calculated for which R(h, h′) is about equal to 1. It is essential to appreciate that this methodology is applicable to many classes of computer vision algorithms, and not only to stereo algorithms.
- the resulting histogram, or self-consistency distribution is an estimate of the reliability of the algorithm's hypotheses, conditionalized by the score of the hypotheses (and also implicitly conditionalized by the class of scenes and observation conditions).
- this distribution remains approximately constant over many scenes (within a given class) then this distribution can be used as a prediction of the reliability of that algorithm applied to just one observation of a new scene.
- the self-consistency methodology presented in the present invention is useful in many fields. For one, it is very useful for any practitioner of computer vision or artificial intelligence that needs an estimate of the reliability of a given inference algorithm applied to a given class of scenes. Also, the self-consistency methodology can be used to eliminate unreliable hypotheses, optimally combine the remaining hypotheses into a more accurate hypothesis (per referent), and clearly identify places where combined hypotheses are insufficiently accurate for some stated purpose. For example, there is a strong need from both civilian and military organizations to estimate the 3-D shape of terrain from aerial images. Current techniques require large amounts of manual editing, with no guarantee of the resulting product. The methodology could be used to produce more accurate shape models by optimally combining hypotheses, as stated above, and to identify places where manual editing is required.
- the self-consistency methodology has a significant advantage over the prior art use of ground truth because the establishment of sufficient quantities of highly accurate and reliable ground truth to estimate reliability is prohibitively expensive, whereas minimal effort beyond data gathering is required for applying the self-consistency methodology
- the hypothesis h produced by a traditional stereo algorithm is a pair of image coordinates (x 0 , x 1 ) in each of two images, (I 0 , I 1 ).
- a stereo match hypothesis h asserts that the closest opaque surface element along the optic ray through x 1 . That is, the referent of h, Ref(h), is the closest opaque surface element along the optic rays through both x 0 and x 1 .
- the self-consistency distribution is the histogram of normalized differences in triangulated 3D points for pairs of matches with a common point in one image.
- the self-consistency distribution should be computed using all possible variations of viewpoint and camera parameters (within some class of variations) over all possible scenes (within some class of scenes).
- an estimate of the distribution can be computed using some small number of images of a scene, and an average distribution over many scenes.
- a fixed collection of images assumed to have been taken at exactly the same time (or, equivalently, a collection of images of a static scene taken over time).
- Each image has a unique index and associated projection matrix and (optionally) projection covariances, which are supposed to be known.
- the projection matrix describes the projective linear relationship between the three-dimensional coordinates of a point in a common coordinate system, and its projection on an image. It should be appreciated that although the methodology is easier to apply when the coordinate system is Euclidean, the minimal requirement is that the set of projection matrices be a common projective coordinate system.
- the output of a point correspondence algorithm is a set of matches of two-dimensional point and, optionally, a score that represents a measure of the algorithm's confidence in the corresponding match. The score would have a low value when the match is certain and a high value when the match is uncertain.
- the image indices, match coordinates and score are reported in match files for each image pair.
- the match files are searched for pairs of matches that have the same coordinate in one image. For example, as illustrated in FIG. 1 , a match is derived from images 1 and 2 , another match is derived from images 1 and 3 , and these two matches have the same coordinate in image 1 , then these two matches have the same referent.
- a pair of matches which is called a common-point match set, should be self-consistent because they should correspond to the same point in the world. This extends the principle of the trinocular stereo constraint to arbitrary camera configurations and multiple images.
- the above methodology is first applied to the output of a simple stereo algorithm.
- the algorithm first rectifies the input pair of images and then searches for 7 ⁇ 7 windows along scan lines that maximize a normalized cross-correlation metric. Sub-pixel accuracy is achieved by fitting a quadratic to the metric evaluated at the pixel and its two adjacent neighbors.
- the algorithm first computes the match by comparing the left image against the right and then comparing the right image against the left. Matches that are not consistent between the two searches are eliminated. Note that this is a way of using self-consistency as a filter.
- the stereo algorithm was applied to all pairs of five aerial images of bare terrain, one of which is illustrated in FIG. 2(a) . These images are actually small windows from much larger images (about 9000 pixels on a side) for which precise ground control and bundle adjustment were applied to get accurate camera parameters. Because the scene depicted in FIG. 2(a) consisted of bare, relatively smooth terrain with little vegetation, it would be expected that the stereo algorithm described would perform well. This expectation is confirmed anecdotally by visually inspecting the matches.
- FIGS. 2(c) and 2(d) show two versions of the distribution.
- the solid curve is the probability density (the probability that the normalized distance equals x). It is useful for seeing the mode and the general shape of the distribution.
- the dashed curve is the cumulative probability distribution (the probability that the normalized distance is less than x). It is useful for seeing the median of the distribution (the point where the curve reaches 0.5) or the fraction of match pairs with normalized distances exceeding some value.
- the self-consistency distribution shows that the mode is about 0.5, about 95% of the normalized distances are below 1, and that about 2% of the match pairs have normalized distances above 10.
- FIG. 2(d) the self-consistency distribution is shown for the same algorithm applied to all pairs of five aerial images of a tree canopy, one of which is illustrated in FIG. 2(b) .
- Such scenes are notoriously difficult for stereo algorithms.
- Visual inspection of the output of the stereo algorithm confirms that most matches are quite wrong. This can be quantified using the self-consistency distribution in FIG. 2(d) . It is seen that, although the mode of the distribution is still about 0.5, only 10% of the matches have a normalized distance of less than 1, and only 42% of the matches have a normalized distance of less than 10.
- the global self-consistency distribution while useful, is only a weak estimate of the accuracy of the algorithm. This is clear from the above examples, in which the unconditional self-consistency distribution varied considerably from one scene to the next.
- the self-consistency distribution for matches having a given “score” can be computed. This is illustrated in FIGS. 2(e) and 2(f) using a scatter diagram.
- the scatter diagram shows a point for every pair of matches, the x coordinate being the normalized distance between the matches.
- the vector x is defined by concatenating the 2-D coordinates of each point of the match, e.g. [x 1 ; y 1 ; x 2 ; y 2 ; . . . x n ; y n ] and the result of the function is the 3-D coordinates X, Y, Z of the point M reconstructed from the match, in the least-squares sense.
- the squared Mahalanobis distance in 3D follows a chi-square distribution with three degrees of freedom:
- ⁇ 3 2 1 2 ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ e - x / 2
- the Mahalanobis distance is computed between M, M′, reconstructions in 3D, which are obtained from matches m i , m′ j of which coordinates are assumed to be Gaussian, zero-mean and with standard deviation a. If M, M′ are obtained from the coordinates m i , m′ j with a linear transformation A, A′, then the covariances are ⁇ 2 AA T , ⁇ 2 A′A′ T .
- the Mahalanobis distance follows the distribution:
- the self-consistency distributions should be statistically independent of the 3D points and projection matrices.
- the Euclidean distance was used, there would be no reason to expect such an independence.
- the model describes the average self-consistency curves very well when the projection matrices are affine (as expected from the theory), but also when they are obtained by perturbation of a fixed matrix.
- the model does not describe the curves very well, but the different self-consistency curves corresponding to each noise level are still distinguishable.
- each image is a window of about 900 pixels on a side from images of about 9000 pixels on a side.
- a single self-consistency distribution for each algorithm was created by merging the scatter data for that algorithm across all seventeen scenes. Previous two algorithms have been compared, but using data from only four images. By merging the scatter data as done here, it is now possible to compare algorithms using data from many scenes. This results in a much more comprehensive comparison.
- the merged distributions are shown in FIG. 5 as probability density functions for the two algorithms.
- the solid curve represents the distribution for the deformable mesh algorithm, and the dashed curve represents the distribution for the stereo algorithm described above.
- FIGS. 2(e) and 2(f) illustrated how a scoring function might be used to segregate matches according to their expected self-consistency.
- the MDL score has the very nice property that the confidence interval (as defined earlier) rises monotonically with the score, at least until there is a paucity of data, when then score is greater than 2. It also has a broad range of scores (those below zero) for which the normalized distances are below 1, with far fewer outliers than the other scores.
- the SSD/GRAD score also increases monotonically (with perhaps a shallow dip for small values of the score), but only over a small range.
- the traditional SSD score is distinctly not monotonic. It is fairly non-self-consistent for small scores, then becomes more self-consistent, and then rises again.
- FIG. 7 presents one image from six urban scenes, where each scene comprised four images.
- FIG. 8(a) shows the merged scatter diagrams and
- FIG. 8(b) shows the global self-consistency distributions for all six scenes, for three window sizes (7 ⁇ 7, 15 ⁇ 15, and 29 ⁇ 29).
- One application of the self-consistency distribution is detecting changes in a scene over time. Given two collections of images of a scene taken at two points in time, matches (from different times) can be compared that belong to the same surface element to see if the different in triangulated coordinates exceeds some significance level.
- the task of finding a pair of matches that refers to the same surface element becomes straightforward: find a pair of matches whose world (x, y) coordinates are approximately the same.
- the self-consistency distribution can be used to find the largest normalized difference that is expected, say, 99% of the time. This is the 99% significance level for detecting change. If the normalized difference exceeds this value, then the difference is due to a change in the terrain.
- FIG. 9(a) is one of 4 images of the scene at time t 1
- FIG. 9(b) is one of six images of the scene at time t 2 . Note the new buildings near the center of the image.
- FIG. 9(c) shows all significant differences found between all pairs of images at times t 1 and t 2 for a window size of 29 ⁇ 29 (applied to a central region of the images).
- FIG. 9(d) shows the union of all significant differences found between matches derived from all pairs of images taken at time to and all pairs of images taken at time t 2 . The majority of the significant differences were found at the location of the new building.
- FIG. 10 is a block diagram of process 100 for estimating the accuracy of inference algorithms using self-consistency methodology.
- step 110 of process 100 a number of observations of a static scene are taken.
- An inference algorithm takes an observation as input and produces a set of hypotheses about the output.
- An observation is one or more images of a static scene taken at the same time and perhaps accompanied by meta-data, such as the time the image(s) was acquired, the internal and external parameters, and their covariances.
- a hypothesis nominally refers to some aspect or element of the world (as opposed to some aspect of the observation), and it normally estimates some attribute of the element it refers to.
- a fixed collection of images is taken at exactly the same time.
- a collection of images of a static scene is taken over time.
- Each image has a unique index and associated projection matrix and (optionally) projection covariances, which are supposed to be known.
- the projection matrix describes the projective linear relationship between the three-dimensional coordinates of a point in a common coordinate system, and its projection on an image. It should be appreciated that although the methodology is easier to apply when the coordinate system is Euclidean, the minimal requirement is that the set of projection matrices be a common projective coordinate system.
- step 120 of process 100 the inference algorithm is applied independently to each observation.
- step 130 of process 100 a statistical analysis is performed. For every pair of hypotheses for which the probability that the first hypothesis refers to the same object in the world as the second hypothesis is close to 1, a histogram is created. The histogram is incremented by a function of an estimate of some well-defined attribute of the referent of the hypothesis and by the covariance of the hypothesis. Optionally, as shown in step 140 , the histogram may be conditionalized on a score.
- the resulting histogram (or self-consistency distribution) is an estimate of the reliability of the algorithm's hypotheses, optionally conditionalized by the score of the hypotheses.
- step 150 of process 100 the inference algorithm is adjusted according to the resulting histogram, to provide a more accurate and self-consistent inference algorithm.
- FIG. 20 is a block diagram of one embodiment of device 200 for hosting a method for estimating an accuracy of an inference process in accordance with the present invention.
- device 200 is any type of intelligent electronic device (e.g., a desktop or laptop computer system, a portable computer system or personal digital assistant, a cell phone, a printer, a fax machine, etc.).
- device 200 includes an address/data bus 201 for communicating information, a central processor 250 coupled with the bus 201 for processing information and instructions, a volatile memory 210 (e.g., random access memory, RAM) coupled with the bus 201 for storing information and instructions for the central processor 250 , and a non-volatile memory 230 (e.g., read only memory, ROM) coupled with the bus 201 for storing static information and instructions for the processor 250 .
- Device 200 also includes an optional data storage device 290 (e.g., a memory stick) coupled with the bus 201 for storing information and instructions. Data storage device 290 can be removable.
- Device 200 also optionally contains a display device 240 coupled to the bus 201 for displaying information to the computer user.
- device 200 of FIG. 20 includes host interface circuitry 220 coupled to bus 201 .
- Host interface circuitry 220 includes an optional digital signal processor (DSP) 222 for processing data to be transmitted or data that are received via a transceiver.
- DSP digital signal processor
- processor 250 can perform some or all of the functions performed by DSP 222 .
- Alphanumeric input device 260 can communicate information and command selections to processor 250 via bus 201 .
- Device 200 also includes an optional cursor control or directing device (on-screen cursor control 280 ) coupled to bus 201 for communicating user input information and command selections to processor 250 .
- on-screen cursor control device 280 is a mouse or touchpad device incorporated with display device 240 .
- On-screen cursor control device 280 is capable of registering a position on display device 240 .
- the display device 240 utilized with device 200 may be a liquid crystal display (LCD) device, a cathode ray tube (CRT), a field emission display device (also called a flat panel CRT), or other display device suitable for generating graphic images and alphanumeric characters recognizable to the user.
- a general formalization of a perceptual observation called self-consistency has been presented, and have proposed a methodology based on this formalization as a means of estimating the accuracy and reliability of point-correspondence algorithms, comparing different stereo algorithms, comparing different scoring functions, comparing window sizes, and detecting change over time.
- a detailed prescription for applying this methodology to multiple-image point-correspondence algorithms has been presented, without any need for ground truth or camera calibration, and have demonstrated it's utility in several experiments.
- the self-consistency distribution is an idea that has powerful consequences. It can be used to compare algorithms, compare scoring functions, evaluate the performance of an algorithm across different classes of scenes, tune algorithm parameters (such as window size), reliably detect changes in a scene, and so forth. All of this can be done for little manual cost beyond the precise estimation of the camera parameters and perhaps manual inspection of the output of the algorithm on a few images to identify systematic biases.
- Section 2 The general self-consistency formalism developed in Section 2, which examines the self-consistency of an algorithm across independent experimental trials of different viewpoints of a static scene, can be used to assess the accuracy and reliability of algorithms dealing with a range of computer vision problems. This could lead to algorithms that can learn to be self-consistent over a wide range of scenes without the need for external training data or “ground truth.”
- the accuracy of the 3-D model is estimated using a general methodology, called self-consistency, for estimating the accuracy of computer vision algorithms, which does not require prior establishment of “ground truth”.
- a novel image-matching measure based on Minimum Description Length (MDL) theory allows for estimating the accuracy of individual elements of the 3-D model. Experiments to demonstrate the utility of the procedure are presented.
- Detecting where an object's 3-D shape has changed requires not only the ability to model shape from images taken at different times, but also the ability to distinguish significant from insignificant differences in the models derived from two image sets.
- This methodology allows for estimating, for a given 3-D reconstruction algorithm and class of scenes, the expected variation in the 3-D reconstruction of objects as a function of viewing geometry and local image-matching quality (referred to as a “score”). Differences between two 3-D reconstructions of an object that exceed this expected variation for a given significance level are deemed to be due to a change in the object's shape, while those below this are deemed to be due to uncertainty in the reconstructions.
- the methodology for change detection presented is based on two simplifying assumptions.
- First, the specific class of objects that is used here is terrain (both urban and rural) viewed from above using aerial imagery.
- the self-consistency methodology can be used to automatically and reliably detect changes in terrain and/or buildings over time.
- the approach consists of several key steps. In brief, the steps are:
- the major advantage in this approach is the statistical measurement of the reliability of a specific stereo algorithm applied to a specific class of scenes. This eliminates the need for ad hoc thresholds for detecting change.
- This approach is useful for any company seeking to provide services to cities and other government agencies that need to know when significant changes have occurred over an area.
- Specific applications include: (a) automatically detecting changes in building height and/or shape or tax purposes, (b) automatically detecting changes in terrain after emergencies such as floods or earthquakes.
- This is also useful for any company currently selling satellite images that are seeking to provided “added value” to their current products (typically raw and rectified images).
- This technology can also be applied to the detection of changes in the 3-D shape of arbitrary objects that can be modeled as single-valued functions of (x, y), such as certain car parts.
- Resampling theory is used to compare the mean or median elevation for each change in the models. Resampling theory is a more specialized application of change detection. It is useful, for example, when the scoring function does not segregate well between good and bad matches, but is acceptable for a specific scene. It should be noted that the comparison of other statistics may also be useful.
- the use of resampling theory requires at least 3 images per point in time. It should also be noted that resampling theory is less reliable than self-consistency methodology when there are fewer than about 5 images per point in time.
- the self-consistency methodology makes it possible to measure the expected variation in the output of a computer vision algorithm as a function of viewing geometry and contextual measures, for a given algorithm and a given class of scenes.
- This expected variation can be expressed as a probability distribution that is called the self-consistency distribution. It is computed from sets of images by independent applications of the algorithm to subsets of images, and in particular does not require the knowledge of ground truth.
- a stereo algorithm attempts to find matches consisting of a pair of points, one in each image, that both correspond to the same surface clement in the world. Though there are many variations on this theme, a typical stereo algorithm starts with a point in the first image. It searches for a matching point in the second image that maximizes some measure of the similarity of the image in the neighborhood of the two points (e.g. the score).
- the 3-D coordinate of the surface element by triangulation can be estimated.
- the self-consistency distribution in this case is the distribution of differences in the triangulated 3-D coordinates for matches that belong to the same surface element, for all pairs of images of a given static scene.
- the key step in estimating this self-consistency distribution is identifying those matches from different image pairs for which the stereo algorithm is asserting belong to the same surface element.
- the normalization mentioned above divides the measured difference by its expected variance for the given camera parameters and an assumed variance of 1 pixel in match coordinates. Consequently, a normalized difference of 1 unit corresponds to a difference in disparity of about 1 pixel for that particular pair of images.
- the self-consistency distribution remains reasonably constant over many scenes taken at the same instant.
- the average of these distributions can be used to represent the self-consistency distribution of new images of a new scene within the same class.
- this average distribution can be used to predict the expected variation in reconstruction when there is only a single image pair of a new scene within the same class.
- the idea is to use the score as a predictor of self-consistency. Since self-consistency is correlated with the quality of reconstruction, it is hoped that with a suitable score, the reconstructions will be similar for places where the match score was good and dissimilar otherwise. The use of a score which has this property is essential for the proposed change detection method to work.
- the present invention uses a score based on Minimum Description Length (MDL) theory is used. It has a stronger correlation with self-consistency than other scores examined, in particular the SSD residual.
- MDL Minimum Description Length
- SSD sum-of-squared-differences
- the coding loss is a measure that satisfies this intuitive requirement. It is the difference between two different ways of encoding the pixels in the correlation windows. It is based on Minimum Description Length (MDL) theory.
- MDL theory quantized observations of a random process are encoded using a model of that process. This model is typically divided into two components: a parameterized predictor function M(z) and the residuals (differences) between the observations and the values predicted by that function.
- the residuals are typically encoded using an i.i.d. noise model.
- MDL is basically a methodology for computing the parameters z that yield the optimal lossless code length for this model and for a given encoding scheme.
- these gray levels can be expressed in terms of the mean gray level g i across images and the deviations (g i j ⁇ g i ) from this average in each individual image.
- C j d M ⁇ (log ⁇ j d+ c) where ⁇ j d is the measured variance of those deviations in image j. Note that, because the mean is described across the images, only N ⁇ 1 of the C j d need by described. The description of the N th one is implicit.
- the MDL score is the difference between these two coding lengths, normalized by the number of samples, that is
- significance level curves are extracted for the values of significance s% (e.g. percent confidence in the significance of the change). For a given value of the score (the x-axis), this is the normalized difference below which s% of the common-xy-coordinate match pairs with that score lie.
- FIG. 11 illustrates several representations of the common-xy-coordinate self-consistency distribution.
- the images ad a ground resolution of approximately 15 cm.
- the bar graph of FIG. 11(b) is the histogram of the normalized difference in the z coordinate of the triangulation of all common-xy-coordinate match pairs. It can be seen from this histogram that the mode of the differences is about 1 normalized unit.
- the curve is the integral of this graph, or the cumulative distribution function. It can be seen from this that about 90% of the match pairs have normalized z differences below 2 units.
- Each point in FIG. 11(a) corresponds to a common-xy-coordinate match pair.
- the x-coordinate of the point in the diagram is the larger of the scores for the two matches, and the y-coordinate is the normalized difference between their triangulated z coordinates.
- the curve in FIG. 11(a) is the 99% significance level. Note that significance level increases as the score increases, indicating that matches with larger scores are less self-consistent than matches with a lower score, an indication of the quality of the MDL score.
- the drop that observed for positive values of the score is due to the fact that there are only few common-xy-coordinate match pairs with positive scores, so that calculations done with those values are not statistically meaningful.
- FIG. 13 shows the changes detected in one of the rural scenes mentioned above, using the deformable mesh algorithm.
- FIG. 13(a) illustrates one of 5 images of the scene taken in 1995. The dark diagonal near the center of the image is a dried creek bed.
- FIG. 13(b) shows one of 5 images of the same area taken in 1998. The dried creek bed as been filled in with dirt, creating a change in elevation of about 1 meter.
- the deformable mesh algorithm is applied to one pair of images taken in 1995. This is then compared to the deformable mesh derived from one pair of images taken in 1998. Vertices that were deemed to be significantly different (above the 99% level of the self-consistency distribution of FIG. 12 (a)), are overlaid as white cross on the image in FIG. 13(c) , which is a magnified view of the dried creek bed of FIG. 13(a) .
- the algorithm has also been applied to forested areas of the same rural scene. Although the normalized differences in z-coordinates is sometimes much larger (10 meters), no changes were deemed significant. Indeed, it is known that the mesh algorithm performs poorly on images of tree canopies, so that reconstruction noise could account for the differences.
- FIGS. 18 and 19 illustrate the results of change detection for two other urban scenes, one with a new building, the other without significant changes.
- FIG. 21 is a flowchart showing the steps in a process 300 for detecting changes in 3-D shape using self-consistency methodology or resampling theory.
- step 310 of process 300 a number of images at different points in time are collected.
- the images can be of any 3-D object or landscape.
- the subject matter of image is not intended to be limited in any way.
- a plurality of overlapping images per point in time are required, although more images improves the accuracy and reliability.
- step 330 of process 300 the user determines whether to analyze the collected images by self-consistency methodology or by resampling theory.
- Steps 340 to 360 of process 300 represent the use of self-consistency methodology to detect changes in 3-D shape.
- Step 370 represents the resampling theory.
- a “score” (e.g. the MDL-based score, see Part II, Section 2.3, supra) is computed for each model element.
- the score is an estimate of the confidence of the accuracy of the 3-D reconstruction algorithms.
- step 350 of process 300 a statistical analysis on the 3-D models is performed. Statistics are collected on the variation in model elevations, as a function of the score. The statistics are merged over all representative images.
- step 360 of process 300 the models derived at one point in time are compared against the models derived at another point in time. Using the statistics of step 350 , it is determined which changes in the models are statistically significantly different. In one embodiment this step can be used when there are as few as two images for each point in time.
- the resampling theory is used to compare the mean or median elevation for each change in the models. It should be noted that the comparison of other statistics may also be useful.
- the use of the resampling theory requires at least 3 images per point in time. It should also be noted that resampling theory is less reliable than self-consistency methodology when there are fewer than about 5 images per point in time.
- the self-consistency methodology has been extended to deal with varying scenes, resulting in a reliable and robust method for detection of changes in 3-D shape.
- the components include: a new image-matching measure called the coding loss; a novel framework for estimating the accuracy and reliability of shape modeling procedures, applicable to other stereo reconstruction procedures; a method for normalizing the effects of camera parameters and their covariances; and a procedure for applying the self-consistency framework.
- This framework could be used with other 3-D attributes.
- the experimental results based on the above framework are promising.
- the framework has been applied to reliably detect quite small changes in terrain (some corresponding to less than a pixel in disparity) in rural scenes using a deformable mesh algorithm, and large changes in urban scenes, which are quite difficult because of occlusions, using a traditional stereo algorithm.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
Description
H−(h1, h2, . . . , hn)=F(Ω, W).
-
- a) Ref(h), the referent of the hypothesis h (e.g. which element in the world that the hypothesis refers to).
- b) R(h, h′)=Prob(Ref(h)=Ref(h′), an estimate of the probability that the two hypotheses h and h′ (computed from two observations of the same world) refer to the same object or process in the world.
- c) Att(h), an estimate of some well-defined attribute of the referent.
- d) Ac(h), an estimate of the accuracy distribution of Att(h). When this is well-modeled by a normal distribution it can be represented implicitly by its covariance, Cov(h).
- e) Score(h), an estimate of the confidence that Att(h) is correct.
C(h, h′)=R(h, h′(Att(h)−Att(h′))T(Cov(h)+Cov(h′)−1(Att(h)−Att(h′))T
-
- a) Collecting many observations of a static scene W. This is done for many static scenes that are within some well-define class of scenes and observation conditions.
- b) The algorithm is applied to each observation of W.
- c) For every hypothesis h(W) and h′(W′) for which R(h,h′) is close to 1, increment the histogram of (Att(h)−Att (h′)) normalized by Acc(h) and Acc(h′) (an example is the Mahalanobis distance: (Att(h)−Att(h′))T(Cov(h)+Cov(h′))−1(Att(h)−Att(h′))). The histogram can be conditionalized on Score(h) and Score(h′).
-
- a) Ref(h), the closest opaque surface element visible along the optic rays through the match points.
- b) R(h, h′)=1 if h and h′ have the same coordinate (within σ) in one image, 0 otherwise.
- c) Atn(h), the triangulated 3D (or projective) coordinates of the surface element.
- d) Acc(h), the covariance of Att(h), given that the match coordinates are N(x0, σ) and N(x0, σ) random variables.
- e) Score(h), a measure such as normalized cross-correlation or sum of squared differences.
-
- 1. General projection matrices are picked randomly.
- 2. Projection matrices are obtained by perturbing a fixed, realistic matrix (which is close to affine). Entries of this matrix are each varied randomly within 500% of the initial value.
- 3. Affine projection matrices are picked randomly.
-
- a) Collecting and controlling imagery of a site at different points in time. At least 2 overlapping images per point in time are required, although more images improves the accuracy and reliability.
- b) Using 3-D reconstruction algorithms 3-D models of the site are created. There will typically be several models per site, one per pair of images taken at one point in time. These models are expected to be incomplete and partially incorrect. A “score” (such as the MDL-based score) is computed for each model element.
- c) [Needed for step 4(a) only]. Applying
steps
- c) [Needed for step 4(a) only]. Applying
- d) Applying
step 2 to a site in question. For every ground coordinate, comparing the models derived at one point in time against the models derived at another point in time.- a) Using the statistics of
step 3 to determine which ground coordinates have elevations that are statistically significantly different. This step can be used when there are as few as two images for each point in time. - b) Using resampling theory to compare the mean or median elevation for each ground coordinate (comparison of other statistics may also be useful). This requires at least 3 images per point in time, but is less reliable than (a) when there are fewer than about 5 images per point in time.
- a) Using the statistics of
Cj=M·(log σj+c)
where σj is the measured variance of the {gi j}1<i≦N and c=½log(2πe).
where
Cj d=M·(log σj d+c)
where σj d is the measured variance of those deviations in image j. Note that, because the mean is described across the images, only N−1 of the Cj d need by described. The description of the Nth one is implicit.
Claims (39)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/645,331 USRE42999E1 (en) | 2000-11-15 | 2006-12-21 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/714,345 US6834120B1 (en) | 2000-11-15 | 2000-11-15 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
US11/645,331 USRE42999E1 (en) | 2000-11-15 | 2006-12-21 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/714,345 Reissue US6834120B1 (en) | 2000-11-15 | 2000-11-15 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
Publications (1)
Publication Number | Publication Date |
---|---|
USRE42999E1 true USRE42999E1 (en) | 2011-12-06 |
Family
ID=33511947
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/714,345 Ceased US6834120B1 (en) | 2000-11-15 | 2000-11-15 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
US11/645,331 Expired - Lifetime USRE42999E1 (en) | 2000-11-15 | 2006-12-21 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/714,345 Ceased US6834120B1 (en) | 2000-11-15 | 2000-11-15 | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology |
Country Status (1)
Country | Link |
---|---|
US (2) | US6834120B1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9953263B2 (en) | 2016-02-11 | 2018-04-24 | International Business Machines Corporation | Performance comparison for determining a travel path for a robot |
Families Citing this family (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
IL146597A0 (en) * | 2001-11-20 | 2002-08-14 | Gordon Goren | Method and system for creating meaningful summaries from interrelated sets of information |
US7835919B1 (en) | 2001-08-10 | 2010-11-16 | Freddie Mac | Systems and methods for home value scoring |
US7711574B1 (en) * | 2001-08-10 | 2010-05-04 | Federal Home Loan Mortgage Corporation (Freddie Mac) | System and method for providing automated value estimates of properties as of a specified previous time period |
WO2003096142A2 (en) * | 2002-05-14 | 2003-11-20 | Gordonomics Ltd. | A system and method for detection and analysis of data |
US7797166B1 (en) | 2002-10-30 | 2010-09-14 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for generating a model for income scoring |
US20040181757A1 (en) * | 2003-03-12 | 2004-09-16 | Brady Deborah A. | Convenient accuracy analysis of content analysis engine |
US8386395B1 (en) | 2005-04-28 | 2013-02-26 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for modifying a loan |
EP1873715A1 (en) * | 2006-06-30 | 2008-01-02 | THOMSON Licensing | Method to estimate the geometric distortion between two images |
US20080147581A1 (en) * | 2006-12-18 | 2008-06-19 | Larimer Daniel J | Processes for Generating Precise and Accurate Output from Untrusted Human Input |
US8126273B2 (en) * | 2007-04-05 | 2012-02-28 | Siemens Corporation | Method for reconstructing three-dimensional images from two-dimensional image data |
US10176827B2 (en) * | 2008-01-15 | 2019-01-08 | Verint Americas Inc. | Active lab |
US10489434B2 (en) | 2008-12-12 | 2019-11-26 | Verint Americas Inc. | Leveraging concepts with information retrieval techniques and knowledge bases |
US8411966B2 (en) * | 2009-03-10 | 2013-04-02 | Her Majesty The Queen In Right Of Canada, As Represented By The Minister Of Industry, Through The Communications Research Centre Canada | Estimation of image relations from point correspondences between images |
US8943094B2 (en) | 2009-09-22 | 2015-01-27 | Next It Corporation | Apparatus, system, and method for natural language processing |
US9122744B2 (en) | 2010-10-11 | 2015-09-01 | Next It Corporation | System and method for providing distributed intelligent assistance |
US9857868B2 (en) | 2011-03-19 | 2018-01-02 | The Board Of Trustees Of The Leland Stanford Junior University | Method and system for ergonomic touch-free interface |
US8840466B2 (en) | 2011-04-25 | 2014-09-23 | Aquifi, Inc. | Method and system to create three-dimensional mapping in a two-dimensional game |
US8686943B1 (en) | 2011-05-13 | 2014-04-01 | Imimtek, Inc. | Two-dimensional method and system enabling three-dimensional user interaction with a device |
US9836177B2 (en) | 2011-12-30 | 2017-12-05 | Next IT Innovation Labs, LLC | Providing variable responses in a virtual-assistant environment |
US8854433B1 (en) | 2012-02-03 | 2014-10-07 | Aquifi, Inc. | Method and system enabling natural user interface gestures with an electronic system |
US9223537B2 (en) | 2012-04-18 | 2015-12-29 | Next It Corporation | Conversation user interface |
US8934675B2 (en) | 2012-06-25 | 2015-01-13 | Aquifi, Inc. | Systems and methods for tracking human hands by performing parts based template matching using images from multiple viewpoints |
US8836768B1 (en) | 2012-09-04 | 2014-09-16 | Aquifi, Inc. | Method and system enabling natural user interface gestures with user wearable glasses |
US9536049B2 (en) | 2012-09-07 | 2017-01-03 | Next It Corporation | Conversational virtual healthcare assistant |
US9129155B2 (en) | 2013-01-30 | 2015-09-08 | Aquifi, Inc. | Systems and methods for initializing motion tracking of human hands using template matching within bounded regions determined using a depth map |
US10318492B2 (en) | 2013-02-25 | 2019-06-11 | Amazon Technologies, Inc. | Predictive storage service |
US9298266B2 (en) | 2013-04-02 | 2016-03-29 | Aquifi, Inc. | Systems and methods for implementing three-dimensional (3D) gesture based graphical user interfaces (GUI) that incorporate gesture reactive interface objects |
US10445115B2 (en) | 2013-04-18 | 2019-10-15 | Verint Americas Inc. | Virtual assistant focused user interfaces |
US9798388B1 (en) | 2013-07-31 | 2017-10-24 | Aquifi, Inc. | Vibrotactile system to augment 3D input systems |
US10928976B2 (en) | 2013-12-31 | 2021-02-23 | Verint Americas Inc. | Virtual assistant acquisitions and training |
US9507417B2 (en) | 2014-01-07 | 2016-11-29 | Aquifi, Inc. | Systems and methods for implementing head tracking based graphical user interfaces (GUI) that incorporate gesture reactive interface objects |
US9619105B1 (en) | 2014-01-30 | 2017-04-11 | Aquifi, Inc. | Systems and methods for gesture based interaction with viewpoint dependent user interfaces |
US20160071517A1 (en) | 2014-09-09 | 2016-03-10 | Next It Corporation | Evaluating Conversation Data based on Risk Factors |
US11568175B2 (en) | 2018-09-07 | 2023-01-31 | Verint Americas Inc. | Dynamic intent classification based on environment variables |
US11232264B2 (en) | 2018-10-19 | 2022-01-25 | Verint Americas Inc. | Natural language processing with non-ontological hierarchy models |
US11196863B2 (en) | 2018-10-24 | 2021-12-07 | Verint Americas Inc. | Method and system for virtual assistant conversations |
US20210073662A1 (en) * | 2019-09-11 | 2021-03-11 | Insurance Services Office, Inc. | Machine Learning Systems and Methods for Performing Entity Resolution Using a Flexible Minimum Weight Set Packing Framework |
WO2022055858A1 (en) * | 2020-09-08 | 2022-03-17 | Advanced Global Clinical Solutions Inc. | Systems and methods for seizure detection with a statistical analysis and an artificial intelligence analysis |
US12033391B2 (en) * | 2021-12-10 | 2024-07-09 | Ford Global Technologies, Llc | Systems and methods for detecting deep neural network inference quality using image/data manipulation without ground truth information |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5267348A (en) * | 1990-03-09 | 1993-11-30 | Hitachi, Ltd. | Method and system for evaluating and modifying fuzzy knowledge |
US5664027A (en) * | 1993-04-20 | 1997-09-02 | Lucent Technologies Inc. | Methods and apparatus for inferring orientation of lines of text |
US5742704A (en) * | 1993-04-30 | 1998-04-21 | Fuji Xerox Co., Ltd. | Image coding apparatus capable of coding in accordance with an image type |
US5819259A (en) * | 1992-12-17 | 1998-10-06 | Hartford Fire Insurance Company | Searching media and text information and categorizing the same employing expert system apparatus and methods |
US6014453A (en) * | 1995-06-12 | 2000-01-11 | Omron Corporation | Counterfeit detecting method and device to generate counterfeit probability data and apparatus employing same |
US6125208A (en) * | 1994-03-10 | 2000-09-26 | International Business Machines Corp. | Writing recognition unit |
US6262730B1 (en) * | 1996-07-19 | 2001-07-17 | Microsoft Corp | Intelligent user assistance facility |
US6307963B1 (en) * | 1997-06-02 | 2001-10-23 | Matsushita Electric Industrial Co., Ltd. | Image detection method, image detection apparatus, image processing method, image processing apparatus, and medium |
US6330360B1 (en) * | 1996-04-19 | 2001-12-11 | Canon Kabushiki Kaisha | Image processing apparatus and method |
US6380934B1 (en) * | 1998-11-30 | 2002-04-30 | Mitsubishi Electric Research Laboratories, Inc. | Estimating targets using statistical properties of observations of known targets |
US20020157116A1 (en) * | 2000-07-28 | 2002-10-24 | Koninklijke Philips Electronics N.V. | Context and content based information processing for multimedia segmentation and indexing |
US20020180805A1 (en) * | 2001-05-24 | 2002-12-05 | Chickering David Maxwell | System and process for automatically explaining probabilistic predictions |
-
2000
- 2000-11-15 US US09/714,345 patent/US6834120B1/en not_active Ceased
-
2006
- 2006-12-21 US US11/645,331 patent/USRE42999E1/en not_active Expired - Lifetime
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5267348A (en) * | 1990-03-09 | 1993-11-30 | Hitachi, Ltd. | Method and system for evaluating and modifying fuzzy knowledge |
US5819259A (en) * | 1992-12-17 | 1998-10-06 | Hartford Fire Insurance Company | Searching media and text information and categorizing the same employing expert system apparatus and methods |
US5664027A (en) * | 1993-04-20 | 1997-09-02 | Lucent Technologies Inc. | Methods and apparatus for inferring orientation of lines of text |
US5742704A (en) * | 1993-04-30 | 1998-04-21 | Fuji Xerox Co., Ltd. | Image coding apparatus capable of coding in accordance with an image type |
US6125208A (en) * | 1994-03-10 | 2000-09-26 | International Business Machines Corp. | Writing recognition unit |
US6014453A (en) * | 1995-06-12 | 2000-01-11 | Omron Corporation | Counterfeit detecting method and device to generate counterfeit probability data and apparatus employing same |
US6330360B1 (en) * | 1996-04-19 | 2001-12-11 | Canon Kabushiki Kaisha | Image processing apparatus and method |
US6262730B1 (en) * | 1996-07-19 | 2001-07-17 | Microsoft Corp | Intelligent user assistance facility |
US6307963B1 (en) * | 1997-06-02 | 2001-10-23 | Matsushita Electric Industrial Co., Ltd. | Image detection method, image detection apparatus, image processing method, image processing apparatus, and medium |
US6380934B1 (en) * | 1998-11-30 | 2002-04-30 | Mitsubishi Electric Research Laboratories, Inc. | Estimating targets using statistical properties of observations of known targets |
US20020157116A1 (en) * | 2000-07-28 | 2002-10-24 | Koninklijke Philips Electronics N.V. | Context and content based information processing for multimedia segmentation and indexing |
US20020180805A1 (en) * | 2001-05-24 | 2002-12-05 | Chickering David Maxwell | System and process for automatically explaining probabilistic predictions |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9953263B2 (en) | 2016-02-11 | 2018-04-24 | International Business Machines Corporation | Performance comparison for determining a travel path for a robot |
Also Published As
Publication number | Publication date |
---|---|
US6834120B1 (en) | 2004-12-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
USRE42999E1 (en) | Method and system for estimating the accuracy of inference algorithms using the self-consistency methodology | |
US6963662B1 (en) | Method and system for detecting changes in three dimensional shape | |
Dick et al. | Modelling and interpretation of architecture from several images | |
McGlone et al. | Projective and object space geometry for monocular building extraction | |
US7272256B2 (en) | System and method for progressive stereo matching of digital images | |
Huber et al. | Fully automatic registration of multiple 3D data sets | |
US20090252373A1 (en) | Method and System for detecting polygon Boundaries of structures in images as particle tracks through fields of corners and pixel gradients | |
Huang et al. | Semantics-aided 3D change detection on construction sites using UAV-based photogrammetric point clouds | |
CN102804231A (en) | Piecewise planar reconstruction of three-dimensional scenes | |
US7928978B2 (en) | Method for generating multi-resolution three-dimensional model | |
Yan et al. | Estimation of building height using a single street view image via deep neural networks | |
Wang et al. | Automatic extraction of building boundaries using aerial LiDAR data | |
Nyaruhuma et al. | Verification of 2D building outlines using oblique airborne images | |
US7865019B2 (en) | On optimizing template matching via performance characterization | |
Jung et al. | A line-based progressive refinement of 3D rooftop models using airborne LiDAR data with single view imagery | |
Song et al. | Development of comprehensive accuracy assessment indexes for building footprint extraction | |
Leclerc et al. | Measuring the self-consistency of stereo algorithms | |
Stal et al. | Classification of airborne laser scanning point clouds based on binomial logistic regression analysis | |
Hoseinnezhad et al. | Consistency of robust estimators in multi-structural visual data segmentation | |
Agouris et al. | Automated spatiotemporal change detection in digital aerial imagery | |
Daudt et al. | Learning to understand earth observation images with weak and unreliable ground truth | |
Jung et al. | Progressive modeling of 3D building rooftops from airborne Lidar and imagery | |
Chen et al. | Urban damage estimation using statistical processing of satellite images | |
Mohammadi | Point cloud analysis for surface defects in civil structures | |
Suveg et al. | 3D Building Reconstruction by Map Based Generation and Evaluation of Hypotheses. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SRI INTERNATIONAL, CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LECLERC, YVAN G.;LUONG, QUANG-TUAN;FUA, PASCAL;SIGNING DATES FROM 20010308 TO 20010511;REEL/FRAME:019653/0556 Owner name: TRANSPACIFIC IP LTD., TAIWAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SRI INTERNATIONAL;REEL/FRAME:019653/0588 Effective date: 20060713 |
|
AS | Assignment |
Owner name: TRANSPACIFIC KODEX, LLC, DELAWARE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TRANSPACIFIC IP LTD.;REEL/FRAME:022629/0354 Effective date: 20090416 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
CC | Certificate of correction | ||
FPAY | Fee payment |
Year of fee payment: 12 |