動態追蹤¶

描述

Motion tracking is the process of locating a moving object across time. Kdenlive uses OpenCV (Open Source Computer Vision Library)[1] for motion detection. The results of this effect can be used in other effects by copying the keyframe data generated by the Motion Tracker as position keyframes in the Transform effect, for example.

參數

參數	數值	描述
追蹤器演算法	選取	Sets the algorithm used for motion tracking
關鍵幀間隔	整數	Determines how many keyframes can be skipped when analyzing
框架形狀	選取	Set the shape of the frame
形狀寬度	整數	Set the thickness of the frame shape
形狀顏色	Picker	Set the color of the frame shape. Also determines the color for Blur type Opaque Fill.
模糊	整數	Set the amount of blur for Blur type Median Blur and Gaussian Blur
模糊類型	選取	Select what to do with the framed section

可以使用以下選項：

Tracker algorithm

KCF	Kernelized Correlation Filters (default)
CSRT	Channel and Spatial Reliability Tracking
MOSSE	Minimum Output Sum of Squared Error
MIL	Multiple Instance Learning
MedianFlow
DaSiam	The DaSiamRPN visual tracking algorithm relies on deep-learning models to provide extremely accurate results. Please see note below for installation instructions.
Nano	Nano tracker is a lightweight model and gives good results and is fast.

小訣竅

You may need to experiment with different tracking algorithms to produce good results for your specific use case. See a short comparison of the different tracking algorithms below.

Frame Shape

矩形	預設
橢圓
箭頭

小訣竅

Selecting the right shape type can make the motion tracking better.

Blur Type

無	Do nothing (default)
Median Blur	Apply median blur to rectangle
高斯模糊	Apply Gaussian blur to rectangle
像素化	Pixelate rectangle
Opaque fill	Fill rectangle with shape color

Examples for Blur Type:

kdenlive_effects-motion_tracker_blur_type — Different blur types in action¶

How to Track a Region of a Video¶

The basic workflow for tracking a region is as follows:

kdenlive_effects-motion_tracking_face — Tracking the face of the model¶

Apply the effect to a clip
Select the desired region[2] to track on the Project Monitor
Choose a tracking algorithm
Click on the Analyze button

kdenlive2304_effects-motion_tracker_copy_kf — Options menu¶

When the analysis is done you can export the keyframes to the clipboard by clicking on and choose Copy all keyframes to clipboard. See also Exchanging keyframes.

Tracking algorithms¶

KCF:

Kernelized Correlation Filters

Pros: Accuracy and speed are both better than MIL and it reports tracking failure better than MIL.

Cons: Does not recover from full occlusion.

CSRT:

Channel and Spatial Reliability Tracking.

In the Discriminative Correlation Filter with Channel and Spatial Reliability (DCF-CSR), we use the spatial reliability map for adjusting the filter support to the part of the selected region from the frame for tracking. This ensures enlarging and localization of the selected region and improved tracking of the non-rectangular regions or objects. It uses only 2 standard features (HoGs and Colornames). It also operates at a comparatively lower fps (25 fps) but gives higher accuracy for object tracking.

MOSSE:

Minimum Output Sum of Squared Error

MOSSE uses an adaptive correlation for object tracking which produces stable correlation filters when initialized using a single frame. MOSSE tracker is robust to variations in lighting, scale, pose, and non-rigid deformations. It also detects occlusion based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears. MOSSE tracker also operates at a higher fps (450 fps and even more).

Pros: It is as accurate as other complex trackers and much faster.

Cons: On a performance scale, it lags behind the deep learning based trackers.

MIL:

Multiple Instance Learning

Pros: The performance is pretty good. It does a reasonable job under partial occlusion.

Cons: Tracking failure is not reported reliably. Does not recover from full occlusion.

MedianFlow:

Pros: Excellent tracking failure reporting. Works very well when the motion is predictable and there is no occlusion.

Cons: Fails under large motion.

DaSiam:

The DaSiamRPN visual tracking algorithm relies on deep-learning models to provide extremely accurate results.

In order to use the DaSiam algorithm you need to download the AI models

dasiamrpn_kernel_cls1.onnx

dasiamrpn_kernel_r1.onnx

dasiamrpn_model.onnx

and place them in folder for models

Nano:

Nano tracker is a lightweight model and gives good results and is fast.

In order to use the Nano algorithm you need to download the AI models (model size about 1.9 MB)

nanotrack_backbone_sim.onnx

nanotrack_head_sim.onnx

and place them in the folder for models

Folder for models¶

Linux:

$HOME/.local/share/kdenlive/opencvmodels

Flatpak:

$HOME/.var/app/org.kde.kdenlive/data/kdenlive/opencvmodels

MacOS:

$HOME/Library/Application Support/kdenlive/opencvmodels

Windows:

%AppData%/kdenlive/opencvmodels

Press Win+R (Windows key and R key simultaneously) and copy %AppData%/kdenlive/. Then create the folder opencvmodels

Windows Only!

You may get an error of mlt_repository_init: failed to dlopen C:\Program Files\kdenlive\lib\mlt/libmltjack.dll or animation initialized FAILED followed by many lines of Current Frame: <f>, percentage: <p>.

In this case it is recommended to delete all kdenlive folders in C:\Program Files\, %AppData%\Roaming\, and %AppData%\Local\, and then do a new install of Kdenlive.