-
Notifications
You must be signed in to change notification settings - Fork 182
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
9 changed files
with
370 additions
and
9 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
273 changes: 273 additions & 0 deletions
273
photon-core/src/main/java/org/photonvision/vision/pipeline/DnnPipeline.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,273 @@ | ||
| /* | ||
| * Copyright (C) Photon Vision. | ||
| * | ||
| * This program is free software: you can redistribute it and/or modify | ||
| * it under the terms of the GNU General Public License as published by | ||
| * the Free Software Foundation, either version 3 of the License, or | ||
| * (at your option) any later version. | ||
| * | ||
| * This program is distributed in the hope that it will be useful, | ||
| * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| * GNU General Public License for more details. | ||
| * | ||
| * You should have received a copy of the GNU General Public License | ||
| * along with this program. If not, see <https://www.gnu.org/licenses/>. | ||
| */ | ||
|
|
||
| package org.photonvision.vision.pipeline; | ||
|
|
||
| import java.util.ArrayList; | ||
| import java.util.List; | ||
| import org.opencv.core.Core; | ||
| import org.opencv.core.Mat; | ||
| import org.opencv.core.MatOfFloat; | ||
| import org.opencv.core.MatOfInt; | ||
| import org.opencv.core.MatOfRect2d; | ||
| import org.opencv.core.Point; | ||
| import org.opencv.core.Rect2d; | ||
| import org.opencv.core.Scalar; | ||
| import org.opencv.core.Size; | ||
| import org.opencv.dnn.Dnn; | ||
| import org.opencv.dnn.Net; | ||
| import org.opencv.imgproc.Imgproc; | ||
| import org.opencv.utils.Converters; | ||
| import org.photonvision.common.util.ColorHelper; | ||
| import org.photonvision.vision.frame.Frame; | ||
| import org.photonvision.vision.frame.FrameThresholdType; | ||
| import org.photonvision.vision.pipe.impl.*; | ||
| import org.photonvision.vision.pipeline.result.CVPipelineResult; | ||
| import org.photonvision.vision.target.TrackedTarget; | ||
| import org.photonvision.vision.target.TrackedTarget.TargetCalculationParameters; | ||
|
|
||
| public class DnnPipeline extends CVPipeline<CVPipelineResult, DnnPipelineSettings> { | ||
| private final CalculateFPSPipe calculateFPSPipe = new CalculateFPSPipe(); | ||
|
|
||
| private static final FrameThresholdType PROCESSING_TYPE = FrameThresholdType.NONE; | ||
|
|
||
| public DnnPipeline() { | ||
| super(PROCESSING_TYPE); | ||
| settings = new DnnPipelineSettings(); | ||
| } | ||
|
|
||
| Net net = null; | ||
| private List<String> outBlobNames = List.of(); | ||
|
|
||
| private List<String> coco_names; | ||
|
|
||
| public DnnPipeline(DnnPipelineSettings settings) { | ||
| super(PROCESSING_TYPE); | ||
| this.settings = settings; | ||
|
|
||
| // Downloaded from https://dev.to/kojix2/yolov7-object-detection-in-ruby-in-10-minutes-5cjh | ||
| // https://s3.ap-northeast-2.wasabisys.com/pinto-model-zoo/307_YOLOv7/with-postprocess/resources_post.tar.gz | ||
| try { | ||
| // this.net = Dnn.readNetFromONNX("/home/matt/Downloads/best_1.onnx"); | ||
| // this.net = Dnn.readNet("/home/matt/Downloads/yolov7_post_640x640.onnx"); | ||
| this.net = | ||
| Dnn.readNetFromDarknet( | ||
| "/home/matt/Downloads/yolov4-csp-swish.cfg", | ||
| "/home/matt/Downloads/yolov4-csp-swish.weights"); | ||
| Core.setNumThreads(8); | ||
| } catch (Exception e) { | ||
| System.out.println(e); | ||
| } | ||
| this.outBlobNames = getOutputNames(net); | ||
|
|
||
| this.coco_names = | ||
| List.of( | ||
| "person", | ||
| "bicycle", | ||
| "car", | ||
| "motorcycle", | ||
| "airplane", | ||
| "bus", | ||
| "train", | ||
| "truck", | ||
| "boat", | ||
| "traffic light", | ||
| "fire hydrant", | ||
| "stop sign", | ||
| "parking meter", | ||
| "bench", | ||
| "bird", | ||
| "cat", | ||
| "dog", | ||
| "horse", | ||
| "sheep", | ||
| "cow", | ||
| "elephant", | ||
| "bear", | ||
| "zebra", | ||
| "giraffe", | ||
| "backpack", | ||
| "umbrella", | ||
| "handbag", | ||
| "tie", | ||
| "suitcase", | ||
| "frisbee", | ||
| "skis", | ||
| "snowboard", | ||
| "sports ball", | ||
| "kite", | ||
| "baseball bat", | ||
| "baseball glove", | ||
| "skateboard", | ||
| "surfboard", | ||
| "tennis racket", | ||
| "bottle", | ||
| "wine glass", | ||
| "cup", | ||
| "fork", | ||
| "knife", | ||
| "spoon", | ||
| "bowl", | ||
| "banana", | ||
| "apple", | ||
| "sandwich", | ||
| "orange", | ||
| "broccoli", | ||
| "carrot", | ||
| "hot dog", | ||
| "pizza", | ||
| "donut", | ||
| "cake", | ||
| "chair", | ||
| "couch", | ||
| "potted plant", | ||
| "bed", | ||
| "dining table", | ||
| "toilet", | ||
| "tv", | ||
| "laptop", | ||
| "mouse", | ||
| "remote", | ||
| "keyboard", | ||
| "cell phone", | ||
| "microwave", | ||
| "oven", | ||
| "toaster", | ||
| "sink", | ||
| "refrigerator", | ||
| "book", | ||
| "clock", | ||
| "vase", | ||
| "scissors", | ||
| "teddy bear", | ||
| "hair drier", | ||
| "toothbrush"); | ||
| } | ||
|
|
||
| @Override | ||
| protected void setPipeParamsImpl() {} | ||
|
|
||
| private static List<String> getOutputNames(Net net) { | ||
| List<String> names = new ArrayList<>(); | ||
|
|
||
| List<Integer> outLayers = net.getUnconnectedOutLayers().toList(); | ||
| List<String> layersNames = net.getLayerNames(); | ||
|
|
||
| outLayers.forEach( | ||
| (item) -> names.add(layersNames.get(item - 1))); // unfold and create R-CNN layers from the | ||
| // loaded YOLO model// | ||
| return names; | ||
| } | ||
|
|
||
| @Override | ||
| protected CVPipelineResult process(Frame input_frame, DnnPipelineSettings settings) { | ||
| long sumPipeNanosElapsed = 0L; | ||
|
|
||
| // ====================== | ||
|
|
||
| var frame = input_frame.colorImage.getMat(); | ||
|
|
||
| if (frame.empty()) { | ||
| return new CVPipelineResult(sumPipeNanosElapsed, 0, List.of(), input_frame); | ||
| } | ||
|
|
||
| var blob = Dnn.blobFromImage(frame, 1.0 / 255.0, new Size(640, 640)); | ||
| net.setInput(blob); | ||
|
|
||
| List<Mat> result = new ArrayList<>(); | ||
| net.forward(result, outBlobNames); // outputlayer : output1 and output2 | ||
|
|
||
| // From https://github.com/suddh123/YOLO-object-detection-in-java/blob/code/yolo.java | ||
|
|
||
| float confThreshold = 0.3f; // Insert thresholding beyond which the model will detect objects// | ||
| List<Integer> clsIds = new ArrayList<>(); | ||
| List<Float> confs = new ArrayList<>(); | ||
| List<Rect2d> rects = new ArrayList<>(); | ||
| for (int i = 0; i < result.size(); ++i) { | ||
| // each row is a candidate detection, the 1st 4 numbers are | ||
| // [center_x, center_y, width, height], followed by (N-4) class probabilities | ||
| Mat level = result.get(i); | ||
| for (int j = 0; j < level.rows(); ++j) { | ||
| Mat row = level.row(j); | ||
| Mat scores = row.colRange(5, level.cols()); | ||
| Core.MinMaxLocResult mm = Core.minMaxLoc(scores); | ||
| float confidence = (float) mm.maxVal; | ||
| Point classIdPoint = mm.maxLoc; | ||
| if (confidence > confThreshold) { | ||
| // scaling for drawing the bounding boxes// | ||
| int centerX = (int) (row.get(0, 0)[0] * frame.cols()); | ||
| int centerY = (int) (row.get(0, 1)[0] * frame.rows()); | ||
| int width = (int) (row.get(0, 2)[0] * frame.cols()); | ||
| int height = (int) (row.get(0, 3)[0] * frame.rows()); | ||
| int left = centerX - width / 2; | ||
| int top = centerY - height / 2; | ||
|
|
||
| clsIds.add((int) classIdPoint.x); | ||
| confs.add((float) confidence); | ||
| rects.add(new Rect2d(left, top, width, height)); | ||
| } | ||
| } | ||
| } | ||
| float nmsThresh = 0.5f; | ||
| MatOfFloat confidences = new MatOfFloat(Converters.vector_float_to_Mat(confs)); | ||
| Rect2d[] boxesArray = rects.toArray(new Rect2d[0]); | ||
| MatOfRect2d boxes = new MatOfRect2d(boxesArray); | ||
| MatOfInt indices = new MatOfInt(); | ||
| Dnn.NMSBoxes( | ||
| boxes, | ||
| confidences, | ||
| confThreshold, | ||
| nmsThresh, | ||
| indices); // We draw the bounding boxes for objects | ||
| // here// | ||
|
|
||
| List<TrackedTarget> targetList = new ArrayList<>(); | ||
|
|
||
| int[] ind = indices.toArray(); | ||
| for (int i = 0; i < ind.length; ++i) { | ||
| int idx = ind[i]; | ||
| var box = boxesArray[idx]; | ||
| Imgproc.rectangle(frame, box.tl(), box.br(), new Scalar(0, 0, 255), 2); | ||
|
|
||
| var name = String.format("%s (%f)", coco_names.get(clsIds.get(idx)), confs.get(idx)); | ||
|
|
||
| Imgproc.putText( | ||
| frame, | ||
| name, | ||
| new Point(box.x + box.width / 2.0, box.y + box.height / 2.0), | ||
| 0, | ||
| 0.6, | ||
| ColorHelper.colorToScalar(java.awt.Color.white), | ||
| 2); | ||
|
|
||
| targetList.add( | ||
| new TrackedTarget( | ||
| box, | ||
| clsIds.get(idx), | ||
| confs.get(idx), | ||
| new TargetCalculationParameters( | ||
| false, null, null, null, null, frameStaticProperties))); | ||
| } | ||
|
|
||
| // ====================== | ||
|
|
||
| var fpsResult = calculateFPSPipe.run(null); | ||
| var fps = fpsResult.output; | ||
|
|
||
| return new CVPipelineResult(sumPipeNanosElapsed, fps, targetList, input_frame); | ||
| } | ||
| } |
24 changes: 24 additions & 0 deletions
24
photon-core/src/main/java/org/photonvision/vision/pipeline/DnnPipelineSettings.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,24 @@ | ||
| /* | ||
| * Copyright (C) Photon Vision. | ||
| * | ||
| * This program is free software: you can redistribute it and/or modify | ||
| * it under the terms of the GNU General Public License as published by | ||
| * the Free Software Foundation, either version 3 of the License, or | ||
| * (at your option) any later version. | ||
| * | ||
| * This program is distributed in the hope that it will be useful, | ||
| * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| * GNU General Public License for more details. | ||
| * | ||
| * You should have received a copy of the GNU General Public License | ||
| * along with this program. If not, see <https://www.gnu.org/licenses/>. | ||
| */ | ||
|
|
||
| package org.photonvision.vision.pipeline; | ||
|
|
||
| public class DnnPipelineSettings extends CVPipelineSettings { | ||
| public DnnPipelineSettings() { | ||
| this.pipelineType = PipelineType.Dnn; | ||
| } | ||
| } |
Oops, something went wrong.