Merge pull request #24913 from usyntest:optical-flow-sample-raft

Raft support added in this sample code #24913

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

fix: https://github.com/opencv/opencv/issues/24424 Update DNN Optical Flow sample with RAFT model
I implemented both RAFT and FlowNet v2 leaving it to the user which one he wants to use to estimate the optical flow.

Co-authored-by: Uday Sharma <uday@192.168.1.35>

samples/dnn/optical_flow.py

@@ -1,13 +1,19 @@
 #!/usr/bin/env python
 '''
-This sample using FlowNet v2 model to calculate optical flow.
-Original paper: https://arxiv.org/abs/1612.01925.
-Original repo:  https://github.com/lmb-freiburg/flownet2.
+This sample using FlowNet v2 and RAFT model to calculate optical flow.
+
+FlowNet v2 Original Paper: https://arxiv.org/abs/1612.01925.
+FlowNet v2 Repo:  https://github.com/lmb-freiburg/flownet2.
 
 Download the converted .caffemodel model from https://drive.google.com/open?id=16qvE9VNmU39NttpZwZs81Ga8VYQJDaWZ
 and .prototxt from https://drive.google.com/file/d/1RyNIUsan1ZOh2hpYIH36A-jofAvJlT6a/view?usp=sharing.
 Otherwise download original model from https://lmb.informatik.uni-freiburg.de/resources/binaries/flownet2/flownet2-models.tar.gz,
 convert .h5 model to .caffemodel and modify original .prototxt using .prototxt from link above.
+
+RAFT Original Paper: https://arxiv.org/pdf/2003.12039.pdf
+RAFT Repo: https://github.com/princeton-vl/RAFT
+
+Download the .onnx model from here https://github.com/opencv/opencv_zoo/raw/281d232cd99cd920853106d853c440edd35eb442/models/optical_flow_estimation_raft/optical_flow_estimation_raft_2023aug.onnx.
 '''
 
 import argparse
@@ -17,8 +23,11 @@ import cv2 as cv
 
 
 class OpticalFlow(object):
-    def __init__(self, proto, model, height, width):
+    def __init__(self, model, height, width, proto=""):
+        if proto:
             self.net = cv.dnn.readNetFromCaffe(proto, model)
+        else:
+            self.net = cv.dnn.readNet(model)
         self.net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
         self.height = height
         self.width = width
@@ -26,8 +35,10 @@ class OpticalFlow(object):
     def compute_flow(self, first_img, second_img):
         inp0 = cv.dnn.blobFromImage(first_img, size=(self.width, self.height))
         inp1 = cv.dnn.blobFromImage(second_img, size=(self.width, self.height))
+        self.net.setInputsNames(["img0", "img1"])
         self.net.setInput(inp0, "img0")
         self.net.setInput(inp1, "img1")
+
         flow = self.net.forward()
         output = self.motion_to_color(flow)
         return output
@@ -46,7 +57,7 @@ class OpticalFlow(object):
         rad = rad[..., np.newaxis] / maxrad
         a = np.arctan2(-fy / maxrad, -fx / maxrad) / np.pi
         fk = (a + 1) / 2.0 * (ncols - 1)
-        k0 = fk.astype(np.int)
+        k0 = fk.astype(np.int32)
         k1 = (k0 + 1) % ncols
         f = fk[..., np.newaxis] - k0[..., np.newaxis]
 
@@ -59,23 +70,26 @@ class OpticalFlow(object):
 
 
 if __name__ == '__main__':
-    parser = argparse.ArgumentParser(description='Use this script to calculate optical flow using FlowNetv2',
+    parser = argparse.ArgumentParser(description='Use this script to calculate optical flow',
                                      formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument('-input', '-i', required=True, help='Path to input video file. Skip this argument to capture frames from a camera.')
     parser.add_argument('--height', default=320, type=int, help='Input height')
     parser.add_argument('--width', default=448, type=int, help='Input width')
-    parser.add_argument('--proto', '-p', default='FlowNet2_deploy_anysize.prototxt', help='Path to prototxt.')
-    parser.add_argument('--model', '-m', default='FlowNet2_weights.caffemodel', help='Path to caffemodel.')
+    parser.add_argument('--proto', '-p', default='', help='Path to prototxt.')
+    parser.add_argument('--model', '-m', required=True, help='Path to model.')
     args, _ = parser.parse_known_args()
 
-    if not os.path.isfile(args.model) or not os.path.isfile(args.proto):
-        raise OSError("Prototxt or caffemodel not exist")
+    if not os.path.isfile(args.model):
+        raise OSError("Model does not exist")
+    if args.proto and not os.path.isfile(args.proto):
+        raise OSError("Prototxt does not exist")
 
     winName = 'Calculation optical flow in OpenCV'
     cv.namedWindow(winName, cv.WINDOW_NORMAL)
     cap = cv.VideoCapture(args.input if args.input else 0)
     hasFrame, first_frame = cap.read()
 
+    if args.proto:
         divisor = 64.
         var = {}
         var['ADAPTED_WIDTH'] = int(np.ceil(args.width/divisor) * divisor)
@@ -93,7 +107,10 @@ if __name__ == '__main__':
 
         caffemodel = open(args.model, 'rb').read()
 
-    opt_flow = OpticalFlow(bytearray(config.encode()), caffemodel, var['ADAPTED_HEIGHT'], var['ADAPTED_WIDTH'])
+        opt_flow = OpticalFlow(caffemodel, var['ADAPTED_HEIGHT'], var['ADAPTED_WIDTH'], bytearray(config.encode()))
+    else:
+        opt_flow = OpticalFlow(args.model, 360, 480)
+
     while cv.waitKey(1) < 0:
         hasFrame, second_frame = cap.read()
         if not hasFrame: