Add DaSiamRPN for object tracking (#15)

* impl wrapper & demo

* add data for object tracking benchmark

* impl benchmark for DaSiamRPN

* update benchmark results for DaSiamRPN

README.md

@@ -36,6 +36,7 @@ Hardware Setup:
 | [PP-ResNet](./models/image_classification_ppresnet) | 224x224 | 56.05 | 602.58 | 98.64 |
 | [PP-HumanSeg](./models/human_segmentation_pphumanseg) | 192x192 | 19.92 | 105.32 | 67.97 |
 | [WeChatQRCode](./models/qrcode_wechatqrcode) | 100x100 | 7.04 | 37.68 | --- |
+| [DaSiamRPN](./models/object_tracking_dasiamrpn) | 1280x720 | 36.15 | 705.48 | 76.82 |
 
 ## License
 

benchmark/benchmark.py

@@ -85,14 +85,14 @@ class Benchmark:
         model.setBackend(self._backend)
         model.setTarget(self._target)
 
-        if 'video' in self._dataloader.name.lower():
-            model.init(self._dataloader.getROI())
-
-        for data in self._dataloader:
-            filename, img = data[:2]
-            size = [img.shape[1], img.shape[0]]
+        for idx, data in enumerate(self._dataloader):
+            filename, input_data = data[:2]
             if filename not in self._benchmark_results:
                 self._benchmark_results[filename] = dict()
+            if isinstance(input_data, np.ndarray):
+                size = [input_data.shape[1], input_data.shape[0]]
+            else:
+                size = input_data.getFrameSize()
             self._benchmark_results[filename][str(size)] = self._metric.forward(model, *data[1:])
 
     def printResults(self):

benchmark/config/object_tracking_dasiamrpn.yaml

@@ -0,0 +1,18 @@
+Benchmark:
+  name: "Object Tracking Benchmark"
+  type: "Tracking"
+  data:
+    type: "TrackingVideoLoader"
+    path: "benchmark/data/object_tracking"
+    files: ["throw_cup.mp4"]
+  metric:
+    type: "Tracking"
+    reduction: "gmean"
+  backend: "default"
+  target: "cpu"
+
+Model:
+  name: "DaSiamRPN"
+  model_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_model_2021nov.onnx"
+  kernel_cls1_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx"
+  kernel_r1_path: "models/object_tracking_dasiamrpn/object_tracking_dasiamrpn_kernel_r1_2021nov.onnx"

benchmark/download_data.py

@@ -184,7 +184,11 @@ data_downloaders = dict(
     qrcode=Downloader(name='qrcode',
         url='https://drive.google.com/u/0/uc?id=1_OXB7eiCIYO335ewkT6EdAeXyriFlq_H&export=download',
         sha='ac01c098934a353ca1545b5266de8bb4f176d1b3',
-        filename='qrcode.zip')
+        filename='qrcode.zip'),
+    object_tracking=Downloader(name='object_tracking',
+        url='https://drive.google.com/u/0/uc?id=1_cw5pUmTF-XmQVcQAI8fIp-Ewi2oMYIn&export=download',
+        sha='0bdb042632a245270013713bc48ad35e9221f3bb',
+        filename='object_tracking.zip')
 )
 
 if __name__ == '__main__':

benchmark/utils/dataloaders/base_dataloader.py

@@ -34,7 +34,7 @@ class _BaseImageLoader:
 class _VideoStream:
     def __init__(self, filepath):
         self._filepath = filepath
-        self._video = cv.VideoCapture(filepath)
+        self._video = cv.VideoCapture(self._filepath)
 
     def __iter__(self):
         while True:
@@ -44,8 +44,21 @@ class _VideoStream:
             else:
                 break
 
+    def __next__(self):
+        while True:
+            has_frame, frame = self._video.read()
+            if has_frame:
+                return frame
+            else:
+                break
+
     def reload(self):
-        self._video = cv.VideoCapture(filepath)
+        self._video = cv.VideoCapture(self._filepath)
+
+    def getFrameSize(self):
+        w = int(self._video.get(cv.CAP_PROP_FRAME_WIDTH))
+        h = int(self._video.get(cv.CAP_PROP_FRAME_HEIGHT))
+        return [w, h]
 
 
 class _BaseVideoLoader:
@@ -56,6 +69,10 @@ class _BaseVideoLoader:
         self._files = kwargs.pop('files', None)
         assert self._files,'Benchmark[\'data\'][\'files\'] cannot be empty.'
 
+        self._streams = dict()
+        for filename in self._files:
+            self._streams[filename] = _VideoStream(os.path.join(self._path, filename))
+
     @property
     def name(self):
         return self.__class__.__name__
@@ -64,4 +81,4 @@ class _BaseVideoLoader:
         return len(self._files)
 
     def __getitem__(self, idx):
-        return self._files[idx], _VideoStream(os.path.join(self._path, self._files[idx]))
+        return self._files[idx], self._streams[idx]

benchmark/utils/dataloaders/tracking.py

@@ -1,3 +1,4 @@
+import os
 import numpy as np
 
 from .base_dataloader import _BaseVideoLoader
@@ -8,18 +9,19 @@ class TrackingVideoLoader(_BaseVideoLoader):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
-        self._rois = self._load_roi()
+        self._first_frames = dict()
+        for filename in self._files:
+            stream = self._streams[filename]
+            self._first_frames[filename] = next(stream)
 
-        unsupported_keys = []
-        for k, _ in kwargs.items():
-            unsupported_keys.append(k)
-        print('Keys ({}) are not supported in Benchmark[\'data\'].'.format(str(unsupported_keys)))
+        self._rois = self._load_roi()
 
     def _load_roi(self):
         rois = dict.fromkeys(self._files, None)
         for filename in self._files:
-            rois[filename] = np.loadtxt(os.path.join(self._path, '{}.txt'.format(filename[:-4])), ndmin=2)
+            rois[filename] = np.loadtxt(os.path.join(self._path, '{}.txt'.format(filename[:-4])), dtype=np.int32, ndmin=2)
         return rois
 
-    def getROI(self):
-        return self._rois
+    def __getitem__(self, idx):
+        filename = self._files[idx]
+        return filename, self._streams[filename], self._first_frames[filename], self._rois[filename]

benchmark/utils/metrics/__init__.py

@@ -1,5 +1,6 @@
 from .base import Base
 from .detection import Detection
 from .recognition import Recognition
+from .tracking import Tracking
 
-__all__ = ['Base', 'Detection', 'Recognition']
+__all__ = ['Base', 'Detection', 'Recognition', 'Tracking']

benchmark/utils/metrics/tracking.py

@@ -0,0 +1,26 @@
+import cv2 as cv
+
+from .base_metric import BaseMetric
+from ..factory import METRICS
+
+@METRICS.register
+class Tracking(BaseMetric):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+        if self._warmup or self._repeat:
+            print('warmup and repeat in metric for tracking do not function.')
+
+    def forward(self, model, *args, **kwargs):
+        stream, first_frame, rois = args
+
+        for roi in rois:
+            stream.reload()
+            model.init(first_frame, tuple(roi))
+            self._timer.reset()
+            for frame in stream:
+                self._timer.start()
+                model.infer(frame)
+                self._timer.stop()
+
+        return self._getResult()

models/__init__.py

@@ -5,6 +5,7 @@ from .face_recognition_sface.sface import SFace
 from .image_classification_ppresnet.ppresnet import PPResNet
 from .human_segmentation_pphumanseg.pphumanseg import PPHumanSeg
 from .qrcode_wechatqrcode.wechatqrcode import WeChatQRCode
+from .object_tracking_dasiamrpn.dasiamrpn import DaSiamRPN
 
 class Registery:
     def __init__(self, name):
@@ -24,4 +25,5 @@ MODELS.register(CRNN)
 MODELS.register(SFace)
 MODELS.register(PPResNet)
 MODELS.register(PPHumanSeg)
-MODELS.register(WeChatQRCode)
+MODELS.register(WeChatQRCode)
+MODELS.register(DaSiamRPN)

models/object_tracking_dasiamrpn/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

models/object_tracking_dasiamrpn/README.md

@@ -0,0 +1,28 @@
+# DaSiamRPN
+
+[Distractor-aware Siamese Networks for Visual Object Tracking](https://arxiv.org/abs/1808.06048)
+
+Note:
+- Model source: [opencv/samples/dnn/diasiamrpn_tracker.cpp](https://github.com/opencv/opencv/blob/ceb94d52a104c0c1287a43dfa6ba72705fb78ac1/samples/dnn/dasiamrpn_tracker.cpp#L5-L7)
+- Visit https://github.com/foolwood/DaSiamRPN for training details.
+
+## Demo
+
+Run the following command to try the demo:
+```shell
+# track on camera input
+python demo.py
+# track on video input
+python demo.py --input /path/to/video
+```
+
+## License
+
+All files in this directory are licensed under [Apache 2.0 License](./LICENSE).
+
+## Reference:
+
+- DaSiamRPN Official Repository: https://github.com/foolwood/DaSiamRPN
+- Paper: https://arxiv.org/abs/1808.06048
+- OpenCV API `TrackerDaSiamRPN` Doc: https://docs.opencv.org/4.x/de/d93/classcv_1_1TrackerDaSiamRPN.html
+- OpenCV Sample: https://github.com/opencv/opencv/blob/4.x/samples/dnn/dasiamrpn_tracker.cpp

models/object_tracking_dasiamrpn/dasiamrpn.py

@@ -0,0 +1,56 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+import numpy as np
+import cv2 as cv
+
+class DaSiamRPN:
+    def __init__(self, model_path, kernel_cls1_path, kernel_r1_path, backend_id=0, target_id=0):
+        self._model_path = model_path
+        self._kernel_cls1_path = kernel_cls1_path
+        self._kernel_r1_path = kernel_r1_path
+        self._backend_id = backend_id
+        self._target_id = target_id
+
+        self._param = cv.TrackerDaSiamRPN_Params()
+        self._param.model = self._model_path
+        self._param.kernel_cls1 = self._kernel_cls1_path
+        self._param.kernel_r1 = self._kernel_r1_path
+        self._param.backend = self._backend_id
+        self._param.target = self._target_id
+        self._model = cv.TrackerDaSiamRPN.create(self._param)
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackend(self, backend_id):
+        self._backend_id = backend_id
+        self._param = cv.TrackerDaSiamRPN_Params()
+        self._param.model = self._model_path
+        self._param.kernel_cls1 = self._kernel_cls1_path
+        self._param.kernel_r1 = self._kernel_r1_path
+        self._param.backend = self._backend_id
+        self._param.target = self._target_id
+        self._model = cv.TrackerDaSiamRPN.create(self._param)
+
+    def setTarget(self, target_id):
+        self._target_id = target_id
+        self._param = cv.TrackerDaSiamRPN_Params()
+        self._param.model = self._model_path
+        self._param.kernel_cls1 = self._kernel_cls1_path
+        self._param.kernel_r1 = self._kernel_r1_path
+        self._param.backend = self._backend_id
+        self._param.target = self._target_id
+        self._model = cv.TrackerDaSiamRPN.create(self._param)
+
+    def init(self, image, roi):
+        self._model.init(image, roi)
+
+    def infer(self, image):
+        isLocated, bbox = self._model.update(image)
+        score = self._model.getTrackingScore()
+        return isLocated, bbox, score

models/object_tracking_dasiamrpn/demo.py

@@ -0,0 +1,95 @@
+# This file is part of OpenCV Zoo project.
+# It is subject to the license terms in the LICENSE file found in the same directory.
+#
+# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
+# Third party copyrights are property of their respective owners.
+
+import argparse
+
+import numpy as np
+import cv2 as cv
+
+from dasiamrpn import DaSiamRPN
+
+def str2bool(v):
+    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
+        return True
+    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
+        return False
+    else:
+        raise NotImplementedError
+
+parser = argparse.ArgumentParser(
+    description="Distractor-aware Siamese Networks for Visual Object Tracking (https://arxiv.org/abs/1808.06048)")
+parser.add_argument('--input', '-i', type=str, help='Path to the input video. Omit for using default camera.')
+parser.add_argument('--model_path', type=str, default='object_tracking_dasiamrpn_model_2021nov.onnx', help='Path to dasiamrpn_model.onnx.')
+parser.add_argument('--kernel_cls1_path', type=str, default='object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx', help='Path to dasiamrpn_kernel_cls1.onnx.')
+parser.add_argument('--kernel_r1_path', type=str, default='object_tracking_dasiamrpn_kernel_r1_2021nov.onnx', help='Path to dasiamrpn_kernel_r1.onnx.')
+parser.add_argument('--save', '-s', type=str2bool, default=False, help='Set true to save results. This flag is invalid when using camera.')
+parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
+args = parser.parse_args()
+
+def visualize(image, bbox, score, isLocated, fps=None, box_color=(0, 255, 0),text_color=(0, 255, 0), fontScale = 1, fontSize = 1):
+    output = image.copy()
+    h, w, _ = output.shape
+
+    if fps is not None:
+        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 30), cv.FONT_HERSHEY_DUPLEX, fontScale, text_color, fontSize)
+
+    if isLocated and score >= 0.6:
+        # bbox: Tuple of length 4
+        x, y, w, h = bbox
+        cv.rectangle(output, (x, y), (x+w, y+h), box_color, 2)
+        cv.putText(output, '{:.2f}'.format(score), (x, y+20), cv.FONT_HERSHEY_DUPLEX, fontScale, text_color, fontSize)
+    else:
+        text_size, baseline = cv.getTextSize('Target lost!', cv.FONT_HERSHEY_DUPLEX, fontScale, fontSize)
+        text_x = int((w - text_size[0]) / 2)
+        text_y = int((h - text_size[1]) / 2)
+        cv.putText(output, 'Target lost!', (text_x, text_y), cv.FONT_HERSHEY_DUPLEX, fontScale, (0, 0, 255), fontSize)
+
+    return output
+
+if __name__ == '__main__':
+    # Instantiate DaSiamRPN
+    model = DaSiamRPN(
+        model_path=args.model_path,
+        kernel_cls1_path=args.kernel_cls1_path,
+        kernel_r1_path=args.kernel_r1_path
+    )
+
+    # Read from args.input
+    _input = args.input
+    if args.input is None:
+        device_id = 0
+        _input = device_id
+    video = cv.VideoCapture(_input)
+
+    # Select an object
+    has_frame, first_frame = video.read()
+    if not has_frame:
+        print('No frames grabbed!')
+        exit()
+    first_frame_copy = first_frame.copy()
+    cv.putText(first_frame_copy, "1. Drag a bounding box to track.", (0, 15), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
+    cv.putText(first_frame_copy, "2. Press ENTER to confirm", (0, 35), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
+    roi = cv.selectROI('DaSiamRPN Demo', first_frame_copy)
+    print("Selected ROI: {}".format(roi))
+
+    # Init tracker with ROI
+    model.init(first_frame, roi)
+
+    # Track frame by frame
+    tm = cv.TickMeter()
+    while cv.waitKey(1) < 0:
+        has_frame, frame = video.read()
+        if not has_frame:
+            print('End of video')
+            break
+        # Inference
+        tm.start()
+        isLocated, bbox, score = model.infer(frame)
+        tm.stop()
+        # Visualize
+        frame = visualize(frame, bbox, score, isLocated, fps=tm.getFPS())
+        cv.imshow('DaSiamRPN Demo', frame)
+        tm.reset()