跳至内容

参考资料 ultralytics/trackers/utils/gmc.py

备注

该文件可在https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/trackers/utils/gmc .py 上获取。如果您发现问题,请通过提交 Pull Request🛠️ 帮助修复。谢谢🙏!



ultralytics.trackers.utils.gmc.GMC

通用运动补偿(GMC)类,用于视频帧中的跟踪和物体检测。

该类提供了基于几种跟踪算法(包括 ORB、 SIFT、ECC 和 Sparse Optical Flow。它还支持缩放帧,以提高计算效率。

属性

名称 类型 说明
method str

用于跟踪的方法。选项包括 "orb"、"sift"、"ecc"、"sparseOptFlow "和 "none"。

downscale int

用于缩放处理帧的系数。

prevFrame ndarray

存储上一帧,以便跟踪。

prevKeyPoints list

存储上一帧的关键点。

prevDescriptors ndarray

存储上一帧的描述符。

initializedFirstFrame bool

指示是否已处理第一帧的标志。

方法

名称 说明
__init__

用指定的方法和缩放因子初始化 GMC 对象。 和缩放因子初始化 GMC 对象。

apply

将所选方法应用于原始帧,并可选择使用 提供的检测。

applyEcc

对原始帧应用 ECC 算法。

applyFeatures

将 ORB 或 SIFT 等基于特征的方法应用于原始帧。

applySparseOptFlow

将稀疏光流方法应用于原始帧。

源代码 ultralytics/trackers/utils/gmc.py
class GMC:
    """
    Generalized Motion Compensation (GMC) class for tracking and object detection in video frames.

    This class provides methods for tracking and detecting objects based on several tracking algorithms including ORB,
    SIFT, ECC, and Sparse Optical Flow. It also supports downscaling of frames for computational efficiency.

    Attributes:
        method (str): The method used for tracking. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'.
        downscale (int): Factor by which to downscale the frames for processing.
        prevFrame (np.ndarray): Stores the previous frame for tracking.
        prevKeyPoints (list): Stores the keypoints from the previous frame.
        prevDescriptors (np.ndarray): Stores the descriptors from the previous frame.
        initializedFirstFrame (bool): Flag to indicate if the first frame has been processed.

    Methods:
        __init__(self, method='sparseOptFlow', downscale=2): Initializes a GMC object with the specified method
                                                              and downscale factor.
        apply(self, raw_frame, detections=None): Applies the chosen method to a raw frame and optionally uses
                                                 provided detections.
        applyEcc(self, raw_frame, detections=None): Applies the ECC algorithm to a raw frame.
        applyFeatures(self, raw_frame, detections=None): Applies feature-based methods like ORB or SIFT to a raw frame.
        applySparseOptFlow(self, raw_frame, detections=None): Applies the Sparse Optical Flow method to a raw frame.
    """

    def __init__(self, method: str = "sparseOptFlow", downscale: int = 2) -> None:
        """
        Initialize a video tracker with specified parameters.

        Args:
            method (str): The method used for tracking. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'.
            downscale (int): Downscale factor for processing frames.
        """
        super().__init__()

        self.method = method
        self.downscale = max(1, downscale)

        if self.method == "orb":
            self.detector = cv2.FastFeatureDetector_create(20)
            self.extractor = cv2.ORB_create()
            self.matcher = cv2.BFMatcher(cv2.NORM_HAMMING)

        elif self.method == "sift":
            self.detector = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
            self.extractor = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
            self.matcher = cv2.BFMatcher(cv2.NORM_L2)

        elif self.method == "ecc":
            number_of_iterations = 5000
            termination_eps = 1e-6
            self.warp_mode = cv2.MOTION_EUCLIDEAN
            self.criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, number_of_iterations, termination_eps)

        elif self.method == "sparseOptFlow":
            self.feature_params = dict(
                maxCorners=1000, qualityLevel=0.01, minDistance=1, blockSize=3, useHarrisDetector=False, k=0.04
            )

        elif self.method in {"none", "None", None}:
            self.method = None
        else:
            raise ValueError(f"Error: Unknown GMC method:{method}")

        self.prevFrame = None
        self.prevKeyPoints = None
        self.prevDescriptors = None
        self.initializedFirstFrame = False

    def apply(self, raw_frame: np.array, detections: list = None) -> np.array:
        """
        Apply object detection on a raw frame using specified method.

        Args:
            raw_frame (np.ndarray): The raw frame to be processed.
            detections (list): List of detections to be used in the processing.

        Returns:
            (np.ndarray): Processed frame.

        Examples:
            >>> gmc = GMC()
            >>> gmc.apply(np.array([[1, 2, 3], [4, 5, 6]]))
            array([[1, 2, 3],
                   [4, 5, 6]])
        """
        if self.method in {"orb", "sift"}:
            return self.applyFeatures(raw_frame, detections)
        elif self.method == "ecc":
            return self.applyEcc(raw_frame)
        elif self.method == "sparseOptFlow":
            return self.applySparseOptFlow(raw_frame)
        else:
            return np.eye(2, 3)

    def applyEcc(self, raw_frame: np.array) -> np.array:
        """
        Apply ECC algorithm to a raw frame.

        Args:
            raw_frame (np.ndarray): The raw frame to be processed.

        Returns:
            (np.ndarray): Processed frame.

        Examples:
            >>> gmc = GMC()
            >>> gmc.applyEcc(np.array([[1, 2, 3], [4, 5, 6]]))
            array([[1, 2, 3],
                   [4, 5, 6]])
        """
        height, width, _ = raw_frame.shape
        frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
        H = np.eye(2, 3, dtype=np.float32)

        # Downscale image
        if self.downscale > 1.0:
            frame = cv2.GaussianBlur(frame, (3, 3), 1.5)
            frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
            width = width // self.downscale
            height = height // self.downscale

        # Handle first frame
        if not self.initializedFirstFrame:
            # Initialize data
            self.prevFrame = frame.copy()

            # Initialization done
            self.initializedFirstFrame = True

            return H

        # Run the ECC algorithm. The results are stored in warp_matrix.
        # (cc, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria)
        try:
            (_, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria, None, 1)
        except Exception as e:
            LOGGER.warning(f"WARNING: find transform failed. Set warp as identity {e}")

        return H

    def applyFeatures(self, raw_frame: np.array, detections: list = None) -> np.array:
        """
        Apply feature-based methods like ORB or SIFT to a raw frame.

        Args:
            raw_frame (np.ndarray): The raw frame to be processed.
            detections (list): List of detections to be used in the processing.

        Returns:
            (np.ndarray): Processed frame.

        Examples:
            >>> gmc = GMC()
            >>> gmc.applyFeatures(np.array([[1, 2, 3], [4, 5, 6]]))
            array([[1, 2, 3],
                   [4, 5, 6]])
        """
        height, width, _ = raw_frame.shape
        frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
        H = np.eye(2, 3)

        # Downscale image
        if self.downscale > 1.0:
            frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
            width = width // self.downscale
            height = height // self.downscale

        # Find the keypoints
        mask = np.zeros_like(frame)
        mask[int(0.02 * height) : int(0.98 * height), int(0.02 * width) : int(0.98 * width)] = 255
        if detections is not None:
            for det in detections:
                tlbr = (det[:4] / self.downscale).astype(np.int_)
                mask[tlbr[1] : tlbr[3], tlbr[0] : tlbr[2]] = 0

        keypoints = self.detector.detect(frame, mask)

        # Compute the descriptors
        keypoints, descriptors = self.extractor.compute(frame, keypoints)

        # Handle first frame
        if not self.initializedFirstFrame:
            # Initialize data
            self.prevFrame = frame.copy()
            self.prevKeyPoints = copy.copy(keypoints)
            self.prevDescriptors = copy.copy(descriptors)

            # Initialization done
            self.initializedFirstFrame = True

            return H

        # Match descriptors
        knnMatches = self.matcher.knnMatch(self.prevDescriptors, descriptors, 2)

        # Filter matches based on smallest spatial distance
        matches = []
        spatialDistances = []

        maxSpatialDistance = 0.25 * np.array([width, height])

        # Handle empty matches case
        if len(knnMatches) == 0:
            # Store to next iteration
            self.prevFrame = frame.copy()
            self.prevKeyPoints = copy.copy(keypoints)
            self.prevDescriptors = copy.copy(descriptors)

            return H

        for m, n in knnMatches:
            if m.distance < 0.9 * n.distance:
                prevKeyPointLocation = self.prevKeyPoints[m.queryIdx].pt
                currKeyPointLocation = keypoints[m.trainIdx].pt

                spatialDistance = (
                    prevKeyPointLocation[0] - currKeyPointLocation[0],
                    prevKeyPointLocation[1] - currKeyPointLocation[1],
                )

                if (np.abs(spatialDistance[0]) < maxSpatialDistance[0]) and (
                    np.abs(spatialDistance[1]) < maxSpatialDistance[1]
                ):
                    spatialDistances.append(spatialDistance)
                    matches.append(m)

        meanSpatialDistances = np.mean(spatialDistances, 0)
        stdSpatialDistances = np.std(spatialDistances, 0)

        inliers = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances

        goodMatches = []
        prevPoints = []
        currPoints = []
        for i in range(len(matches)):
            if inliers[i, 0] and inliers[i, 1]:
                goodMatches.append(matches[i])
                prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt)
                currPoints.append(keypoints[matches[i].trainIdx].pt)

        prevPoints = np.array(prevPoints)
        currPoints = np.array(currPoints)

        # Draw the keypoint matches on the output image
        # if False:
        #     import matplotlib.pyplot as plt
        #     matches_img = np.hstack((self.prevFrame, frame))
        #     matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR)
        #     W = self.prevFrame.shape[1]
        #     for m in goodMatches:
        #         prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
        #         curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
        #         curr_pt[0] += W
        #         color = np.random.randint(0, 255, 3)
        #         color = (int(color[0]), int(color[1]), int(color[2]))
        #
        #         matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)
        #         matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1)
        #         matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1)
        #
        #     plt.figure()
        #     plt.imshow(matches_img)
        #     plt.show()

        # Find rigid matrix
        if prevPoints.shape[0] > 4:
            H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)

            # Handle downscale
            if self.downscale > 1.0:
                H[0, 2] *= self.downscale
                H[1, 2] *= self.downscale
        else:
            LOGGER.warning("WARNING: not enough matching points")

        # Store to next iteration
        self.prevFrame = frame.copy()
        self.prevKeyPoints = copy.copy(keypoints)
        self.prevDescriptors = copy.copy(descriptors)

        return H

    def applySparseOptFlow(self, raw_frame: np.array) -> np.array:
        """
        Apply Sparse Optical Flow method to a raw frame.

        Args:
            raw_frame (np.ndarray): The raw frame to be processed.

        Returns:
            (np.ndarray): Processed frame.

        Examples:
            >>> gmc = GMC()
            >>> gmc.applySparseOptFlow(np.array([[1, 2, 3], [4, 5, 6]]))
            array([[1, 2, 3],
                   [4, 5, 6]])
        """
        height, width, _ = raw_frame.shape
        frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
        H = np.eye(2, 3)

        # Downscale image
        if self.downscale > 1.0:
            frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))

        # Find the keypoints
        keypoints = cv2.goodFeaturesToTrack(frame, mask=None, **self.feature_params)

        # Handle first frame
        if not self.initializedFirstFrame or self.prevKeyPoints is None:
            self.prevFrame = frame.copy()
            self.prevKeyPoints = copy.copy(keypoints)
            self.initializedFirstFrame = True
            return H

        # Find correspondences
        matchedKeypoints, status, _ = cv2.calcOpticalFlowPyrLK(self.prevFrame, frame, self.prevKeyPoints, None)

        # Leave good correspondences only
        prevPoints = []
        currPoints = []

        for i in range(len(status)):
            if status[i]:
                prevPoints.append(self.prevKeyPoints[i])
                currPoints.append(matchedKeypoints[i])

        prevPoints = np.array(prevPoints)
        currPoints = np.array(currPoints)

        # Find rigid matrix
        if (prevPoints.shape[0] > 4) and (prevPoints.shape[0] == prevPoints.shape[0]):
            H, _ = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)

            if self.downscale > 1.0:
                H[0, 2] *= self.downscale
                H[1, 2] *= self.downscale
        else:
            LOGGER.warning("WARNING: not enough matching points")

        self.prevFrame = frame.copy()
        self.prevKeyPoints = copy.copy(keypoints)

        return H

    def reset_params(self) -> None:
        """Reset parameters."""
        self.prevFrame = None
        self.prevKeyPoints = None
        self.prevDescriptors = None
        self.initializedFirstFrame = False

__init__(method='sparseOptFlow', downscale=2)

使用指定参数初始化视频跟踪器。

参数

名称 类型 说明 默认值
method str

用于跟踪的方法。选项包括 "orb"、"sift"、"ecc"、"sparseOptFlow "和 "none"。

'sparseOptFlow'
downscale int

处理帧的缩放因子。

2
源代码 ultralytics/trackers/utils/gmc.py
def __init__(self, method: str = "sparseOptFlow", downscale: int = 2) -> None:
    """
    Initialize a video tracker with specified parameters.

    Args:
        method (str): The method used for tracking. Options include 'orb', 'sift', 'ecc', 'sparseOptFlow', 'none'.
        downscale (int): Downscale factor for processing frames.
    """
    super().__init__()

    self.method = method
    self.downscale = max(1, downscale)

    if self.method == "orb":
        self.detector = cv2.FastFeatureDetector_create(20)
        self.extractor = cv2.ORB_create()
        self.matcher = cv2.BFMatcher(cv2.NORM_HAMMING)

    elif self.method == "sift":
        self.detector = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
        self.extractor = cv2.SIFT_create(nOctaveLayers=3, contrastThreshold=0.02, edgeThreshold=20)
        self.matcher = cv2.BFMatcher(cv2.NORM_L2)

    elif self.method == "ecc":
        number_of_iterations = 5000
        termination_eps = 1e-6
        self.warp_mode = cv2.MOTION_EUCLIDEAN
        self.criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, number_of_iterations, termination_eps)

    elif self.method == "sparseOptFlow":
        self.feature_params = dict(
            maxCorners=1000, qualityLevel=0.01, minDistance=1, blockSize=3, useHarrisDetector=False, k=0.04
        )

    elif self.method in {"none", "None", None}:
        self.method = None
    else:
        raise ValueError(f"Error: Unknown GMC method:{method}")

    self.prevFrame = None
    self.prevKeyPoints = None
    self.prevDescriptors = None
    self.initializedFirstFrame = False

apply(raw_frame, detections=None)

使用指定方法对原始帧进行对象检测。

参数

名称 类型 说明 默认值
raw_frame ndarray

要处理的原始帧。

所需
detections list

用于处理的检测列表。

None

返回:

类型 说明
ndarray

加工过的框架。

例如

>>> gmc = GMC()
>>> gmc.apply(np.array([[1, 2, 3], [4, 5, 6]]))
array([[1, 2, 3],
       [4, 5, 6]])
源代码 ultralytics/trackers/utils/gmc.py
def apply(self, raw_frame: np.array, detections: list = None) -> np.array:
    """
    Apply object detection on a raw frame using specified method.

    Args:
        raw_frame (np.ndarray): The raw frame to be processed.
        detections (list): List of detections to be used in the processing.

    Returns:
        (np.ndarray): Processed frame.

    Examples:
        >>> gmc = GMC()
        >>> gmc.apply(np.array([[1, 2, 3], [4, 5, 6]]))
        array([[1, 2, 3],
               [4, 5, 6]])
    """
    if self.method in {"orb", "sift"}:
        return self.applyFeatures(raw_frame, detections)
    elif self.method == "ecc":
        return self.applyEcc(raw_frame)
    elif self.method == "sparseOptFlow":
        return self.applySparseOptFlow(raw_frame)
    else:
        return np.eye(2, 3)

applyEcc(raw_frame)

对原始帧应用 ECC 算法。

参数

名称 类型 说明 默认值
raw_frame ndarray

要处理的原始帧。

所需

返回:

类型 说明
ndarray

加工过的框架。

例如

>>> gmc = GMC()
>>> gmc.applyEcc(np.array([[1, 2, 3], [4, 5, 6]]))
array([[1, 2, 3],
       [4, 5, 6]])
源代码 ultralytics/trackers/utils/gmc.py
def applyEcc(self, raw_frame: np.array) -> np.array:
    """
    Apply ECC algorithm to a raw frame.

    Args:
        raw_frame (np.ndarray): The raw frame to be processed.

    Returns:
        (np.ndarray): Processed frame.

    Examples:
        >>> gmc = GMC()
        >>> gmc.applyEcc(np.array([[1, 2, 3], [4, 5, 6]]))
        array([[1, 2, 3],
               [4, 5, 6]])
    """
    height, width, _ = raw_frame.shape
    frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
    H = np.eye(2, 3, dtype=np.float32)

    # Downscale image
    if self.downscale > 1.0:
        frame = cv2.GaussianBlur(frame, (3, 3), 1.5)
        frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
        width = width // self.downscale
        height = height // self.downscale

    # Handle first frame
    if not self.initializedFirstFrame:
        # Initialize data
        self.prevFrame = frame.copy()

        # Initialization done
        self.initializedFirstFrame = True

        return H

    # Run the ECC algorithm. The results are stored in warp_matrix.
    # (cc, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria)
    try:
        (_, H) = cv2.findTransformECC(self.prevFrame, frame, H, self.warp_mode, self.criteria, None, 1)
    except Exception as e:
        LOGGER.warning(f"WARNING: find transform failed. Set warp as identity {e}")

    return H

applyFeatures(raw_frame, detections=None)

将 ORB 或 SIFT 等基于特征的方法应用于原始帧。

参数

名称 类型 说明 默认值
raw_frame ndarray

要处理的原始帧。

所需
detections list

用于处理的检测列表。

None

返回:

类型 说明
ndarray

加工过的框架。

例如

>>> gmc = GMC()
>>> gmc.applyFeatures(np.array([[1, 2, 3], [4, 5, 6]]))
array([[1, 2, 3],
       [4, 5, 6]])
源代码 ultralytics/trackers/utils/gmc.py
def applyFeatures(self, raw_frame: np.array, detections: list = None) -> np.array:
    """
    Apply feature-based methods like ORB or SIFT to a raw frame.

    Args:
        raw_frame (np.ndarray): The raw frame to be processed.
        detections (list): List of detections to be used in the processing.

    Returns:
        (np.ndarray): Processed frame.

    Examples:
        >>> gmc = GMC()
        >>> gmc.applyFeatures(np.array([[1, 2, 3], [4, 5, 6]]))
        array([[1, 2, 3],
               [4, 5, 6]])
    """
    height, width, _ = raw_frame.shape
    frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
    H = np.eye(2, 3)

    # Downscale image
    if self.downscale > 1.0:
        frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))
        width = width // self.downscale
        height = height // self.downscale

    # Find the keypoints
    mask = np.zeros_like(frame)
    mask[int(0.02 * height) : int(0.98 * height), int(0.02 * width) : int(0.98 * width)] = 255
    if detections is not None:
        for det in detections:
            tlbr = (det[:4] / self.downscale).astype(np.int_)
            mask[tlbr[1] : tlbr[3], tlbr[0] : tlbr[2]] = 0

    keypoints = self.detector.detect(frame, mask)

    # Compute the descriptors
    keypoints, descriptors = self.extractor.compute(frame, keypoints)

    # Handle first frame
    if not self.initializedFirstFrame:
        # Initialize data
        self.prevFrame = frame.copy()
        self.prevKeyPoints = copy.copy(keypoints)
        self.prevDescriptors = copy.copy(descriptors)

        # Initialization done
        self.initializedFirstFrame = True

        return H

    # Match descriptors
    knnMatches = self.matcher.knnMatch(self.prevDescriptors, descriptors, 2)

    # Filter matches based on smallest spatial distance
    matches = []
    spatialDistances = []

    maxSpatialDistance = 0.25 * np.array([width, height])

    # Handle empty matches case
    if len(knnMatches) == 0:
        # Store to next iteration
        self.prevFrame = frame.copy()
        self.prevKeyPoints = copy.copy(keypoints)
        self.prevDescriptors = copy.copy(descriptors)

        return H

    for m, n in knnMatches:
        if m.distance < 0.9 * n.distance:
            prevKeyPointLocation = self.prevKeyPoints[m.queryIdx].pt
            currKeyPointLocation = keypoints[m.trainIdx].pt

            spatialDistance = (
                prevKeyPointLocation[0] - currKeyPointLocation[0],
                prevKeyPointLocation[1] - currKeyPointLocation[1],
            )

            if (np.abs(spatialDistance[0]) < maxSpatialDistance[0]) and (
                np.abs(spatialDistance[1]) < maxSpatialDistance[1]
            ):
                spatialDistances.append(spatialDistance)
                matches.append(m)

    meanSpatialDistances = np.mean(spatialDistances, 0)
    stdSpatialDistances = np.std(spatialDistances, 0)

    inliers = (spatialDistances - meanSpatialDistances) < 2.5 * stdSpatialDistances

    goodMatches = []
    prevPoints = []
    currPoints = []
    for i in range(len(matches)):
        if inliers[i, 0] and inliers[i, 1]:
            goodMatches.append(matches[i])
            prevPoints.append(self.prevKeyPoints[matches[i].queryIdx].pt)
            currPoints.append(keypoints[matches[i].trainIdx].pt)

    prevPoints = np.array(prevPoints)
    currPoints = np.array(currPoints)

    # Draw the keypoint matches on the output image
    # if False:
    #     import matplotlib.pyplot as plt
    #     matches_img = np.hstack((self.prevFrame, frame))
    #     matches_img = cv2.cvtColor(matches_img, cv2.COLOR_GRAY2BGR)
    #     W = self.prevFrame.shape[1]
    #     for m in goodMatches:
    #         prev_pt = np.array(self.prevKeyPoints[m.queryIdx].pt, dtype=np.int_)
    #         curr_pt = np.array(keypoints[m.trainIdx].pt, dtype=np.int_)
    #         curr_pt[0] += W
    #         color = np.random.randint(0, 255, 3)
    #         color = (int(color[0]), int(color[1]), int(color[2]))
    #
    #         matches_img = cv2.line(matches_img, prev_pt, curr_pt, tuple(color), 1, cv2.LINE_AA)
    #         matches_img = cv2.circle(matches_img, prev_pt, 2, tuple(color), -1)
    #         matches_img = cv2.circle(matches_img, curr_pt, 2, tuple(color), -1)
    #
    #     plt.figure()
    #     plt.imshow(matches_img)
    #     plt.show()

    # Find rigid matrix
    if prevPoints.shape[0] > 4:
        H, inliers = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)

        # Handle downscale
        if self.downscale > 1.0:
            H[0, 2] *= self.downscale
            H[1, 2] *= self.downscale
    else:
        LOGGER.warning("WARNING: not enough matching points")

    # Store to next iteration
    self.prevFrame = frame.copy()
    self.prevKeyPoints = copy.copy(keypoints)
    self.prevDescriptors = copy.copy(descriptors)

    return H

applySparseOptFlow(raw_frame)

将稀疏光流法应用于原始帧。

参数

名称 类型 说明 默认值
raw_frame ndarray

要处理的原始帧。

所需

返回:

类型 说明
ndarray

加工过的框架。

例如

>>> gmc = GMC()
>>> gmc.applySparseOptFlow(np.array([[1, 2, 3], [4, 5, 6]]))
array([[1, 2, 3],
       [4, 5, 6]])
源代码 ultralytics/trackers/utils/gmc.py
def applySparseOptFlow(self, raw_frame: np.array) -> np.array:
    """
    Apply Sparse Optical Flow method to a raw frame.

    Args:
        raw_frame (np.ndarray): The raw frame to be processed.

    Returns:
        (np.ndarray): Processed frame.

    Examples:
        >>> gmc = GMC()
        >>> gmc.applySparseOptFlow(np.array([[1, 2, 3], [4, 5, 6]]))
        array([[1, 2, 3],
               [4, 5, 6]])
    """
    height, width, _ = raw_frame.shape
    frame = cv2.cvtColor(raw_frame, cv2.COLOR_BGR2GRAY)
    H = np.eye(2, 3)

    # Downscale image
    if self.downscale > 1.0:
        frame = cv2.resize(frame, (width // self.downscale, height // self.downscale))

    # Find the keypoints
    keypoints = cv2.goodFeaturesToTrack(frame, mask=None, **self.feature_params)

    # Handle first frame
    if not self.initializedFirstFrame or self.prevKeyPoints is None:
        self.prevFrame = frame.copy()
        self.prevKeyPoints = copy.copy(keypoints)
        self.initializedFirstFrame = True
        return H

    # Find correspondences
    matchedKeypoints, status, _ = cv2.calcOpticalFlowPyrLK(self.prevFrame, frame, self.prevKeyPoints, None)

    # Leave good correspondences only
    prevPoints = []
    currPoints = []

    for i in range(len(status)):
        if status[i]:
            prevPoints.append(self.prevKeyPoints[i])
            currPoints.append(matchedKeypoints[i])

    prevPoints = np.array(prevPoints)
    currPoints = np.array(currPoints)

    # Find rigid matrix
    if (prevPoints.shape[0] > 4) and (prevPoints.shape[0] == prevPoints.shape[0]):
        H, _ = cv2.estimateAffinePartial2D(prevPoints, currPoints, cv2.RANSAC)

        if self.downscale > 1.0:
            H[0, 2] *= self.downscale
            H[1, 2] *= self.downscale
    else:
        LOGGER.warning("WARNING: not enough matching points")

    self.prevFrame = frame.copy()
    self.prevKeyPoints = copy.copy(keypoints)

    return H

reset_params()

重置参数。

源代码 ultralytics/trackers/utils/gmc.py
def reset_params(self) -> None:
    """Reset parameters."""
    self.prevFrame = None
    self.prevKeyPoints = None
    self.prevDescriptors = None
    self.initializedFirstFrame = False





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (5), Burhan-Q (1)