Searched refs:detection (Results 1 - 25 of 29) sorted by relevance

12

/external/webrtc/webrtc/modules/audio_processing/transient/test/
H A DreadDetection.m4 %Reads a detection signal from a DAT file.
6 %d: The detection signal.
9 %file: The DAT file where the detection signal is stored in float format.
11 %chunkSize: The chunk size used for the detection in seconds.
H A DplotDetection.m4 %Plots the signal alongside the detection values.
7 %DATfile: The file containing the detection values in binary float format.
9 %chunkSize: The chunk size used to compute the detection values in seconds.
/external/valgrind/exp-bbv/tests/amd64-linux/
H A Drep_prefix.S15 # Check for them, to make sure our rep detection
/external/tensorflow/tensorflow/examples/android/jni/object_tracking/
H A Dobject_tracker.cc497 const Detection& detection, TrackedObject** match) const {
507 detection.GetObjectBoundingBox());
510 (detection.GetObjectModel() != tracked_object->GetModel())) {
519 detection.GetObjectBoundingBox().GetCenter()).LengthSquared();
532 detection.GetMatchScore()) {
547 LOGV("Initial detection done, iterating over %zu detections now.",
554 const Detection& detection = *it; local
555 SCHECK(frame2_->GetImage()->Contains(detection.GetObjectBoundingBox()),
561 GetBestObjectForDetection(detection, &best_match);
566 const_cast<ObjectModelBase*>(detection
496 GetBestObjectForDetection( const Detection& detection, TrackedObject** match) const argument
[all...]
H A Dconfig.h32 // Struct that can be used to more richly store the results of a detection
46 const MatchScore& detection) {
47 stream << detection.value;
93 // Keypoint detection.
214 // The number of detection failures allowed before an object goes invisible.
244 // examples for detection to be valid.
45 operator <<(std::ostream& stream, const MatchScore& detection) argument
H A Dobject_detector.h79 // Represents a potential detection of a specific ObjectExemplar and Descriptor
127 const Detection& detection) {
128 const BoundingBox actual_area = detection.GetObjectBoundingBox();
147 // Main entry point into the detection algorithm.
H A Dobject_tracker.h51 // ObjectTracker is the highest-level class in the tracking/detection framework.
52 // It handles basic image processing, keypoint detection, keypoint tracking,
53 // object tracking, and object detection/relocalization.
67 // Does all image processing, keypoint detection, and object
68 // tracking/detection for registered objects.
225 const Detection& detection, TrackedObject** match) const;
/external/freetype/builds/
H A Ddetect.mk2 # FreeType 2 host platform detection rules
27 # auto-detection fails.
41 # Set auto-detection default to `ansi' resp. UNIX-like operating systems.
78 # If no setup target platform was specified, enable auto-detection/
86 # disable auto-detection.
89 # Now, include all detection rule files found in the `builds/<system>'
96 # In case no detection rule file was successful, use the default.
114 @echo "$(PROJECT_TITLE) build system -- automatic system detection"
139 @echo $(PROJECT_TITLE) build system -- automatic system detection
/external/tensorflow/tensorflow/examples/android/src/org/tensorflow/demo/tracking/
H A DMultiBoxTracker.java48 // Maximum percentage of a box that can be overlapped by another box at detection time. Otherwise
130 for (final Pair<Float, RectF> detection : screenRects) {
131 final RectF rect = detection.second;
133 canvas.drawText("" + detection.first, rect.left, rect.top, textPaint);
134 borderedText.drawText(canvas, rect.centerX(), rect.centerY(), "" + detection.first);
346 // If track for the existing object is still going strong and the detection score was
387 "Removing tracked object %s with detection confidence %.2f, correlation %.2f",
406 "Tracking object %s (%s) with detection confidence %.2f at position %s",
/external/brotli/research/
H A DREADME.md3 In this directory we publish simple tools to analyze backward reference distance distributions in LZ77 compression. We developed these tools to be able to make more efficient encoding of distances in large-window brotli. In large-window compression the average cost of a backward reference distance is higher, and this may allow for more advanced encoding strategies, such as delta coding or an increase in context size, to bring significant compression density improvements. Our tools visualize the backward references as histogram images, i.e., one pixel in the image shows how many distances of a certain range exist at a certain locality in the data. The human visual system is excellent at pattern detection, so we tried to roughly identify patterns visually before going into more quantitative analysis. These tools can turn out to be useful in development of other LZ77-based compressors and we hope you try them out.
/external/tensorflow/tensorflow/examples/android/src/org/tensorflow/demo/
H A DTensorFlowMultiBoxDetector.java38 * A detector for general purpose object detection as described in Scalable Object Detection using
254 final RectF detection =
260 pq.add(new Recognition("" + i, null, outputScores[i], detection));
H A DTensorFlowObjectDetectionAPIModel.java37 * Wrapper for frozen detection models trained using the Tensorflow Object Detection API:
187 final RectF detection =
194 new Recognition("" + i, labels.get((int) outputClasses[i]), outputScores[i], detection));
/external/libxcam/
H A DREADME.md43 - Face detection interface/plugin.
/external/tensorflow/tensorflow/contrib/lite/models/testdata/g3doc/
H A DREADME.md25 spotting (i.e. "okgoogle" detection). It is the entry point for voice
82 events that allow detection of speech start and end events.
/external/v8/tools/dev/
H A Dv8gen.py111 help='don\'t use goma auto detection - goma might still be used if '
/external/llvm/lib/Support/Unix/
H A DPath.inc178 // Fall back to the classical detection.
/external/swiftshader/third_party/llvm-subzero/lib/Support/Unix/
H A DPath.inc179 // Fall back to the classical detection.
/external/aac/libSBRenc/src/
H A Dmh_det.cpp308 \brief Calculates the input to the missing harmonics detection.
337 \brief Checks that the detection is not due to a LP filter
340 in fact just a low-pass filtere input signal. If so, the detection is
493 * Determine if detection of new missing harmonics are allowed.
520 \brief Cleans up the detection after a transient.
547 /* detection in adjacent channels.*/
631 /* Make sure that the detection is not the cut-off of a low pass filter. */
649 This is the actual missing harmonics detection, using information from the
650 previous detection.
654 current frame, the detection algorith
671 static void detection(FIXP_DBL *quotaBuffer, FIXP_DBL *pDiffVecScfb, INT nSfb, function
[all...]
/external/syslinux/
H A Dsyslinux.spec246 - 1.51pre3, with e820 detection
/external/autotest/site_utils/
H A Dgenerate_test_report699 parser.add_option('--no-crash-detection', dest='crash_detection',
704 'Implies --no-debug --no-crash-detection.')
742 Warning('Forcing --no-debug --no-crash-detection')
/external/libvpx/libvpx/
H A Dconfigure55 ${toggle_runtime_cpu_detect} runtime cpu detection
534 echo "Bypassing toolchain for environment detection."
/external/antlr/antlr-3.4/tool/src/main/resources/org/antlr/codegen/templates/Ruby/
H A DRuby.stg782 * detection but this is faster, smaller, and more what people
/external/mesa3d/docs/specs/
H A DMESA_query_renderer.spec358 device detection based on these strings.
/external/ImageMagick/www/api/
H A Dmorphology.php142 <dd> LoG:{radius},{sigma} "Laplacian of a Gaussian" or "Mexician Hat" Kernel. The supposed ideal edge detection, zero-summing kernel. </dd>
216 <dd> The first 4 are for edge detection, the next 4 are for line detection and the last is to add a average component to the results. </dd>
/external/minijail/
H A Dcommon.mk623 # Architecture detection and QEMU wrapping
708 # Standard targets with detection for when they are improperly configured.

Completed in 2791 milliseconds

12