科研 Skill
动物行为姿态追踪
animal-behavior-tracking
Tracks animal pose and behavior from video with DeepLabCut or SLEAP, and extracts kinematic and behavioral event features. Use for markerless tracking or scoring behavior.
SKILL.md
Animal behavior tracking
Markerless pose estimation (DeepLabCut, SLEAP) turns raw behavior video into labeled body-part trajectories, which then need cleaning, kinematic feature extraction, and often event/state classification before they are useful for correlating with neural data. This skill covers the pipeline from raw video to analysis-ready behavioral features.
When to use this skill
Use it when the user has video of a freely moving or head-fixed animal and needs body-part or whole-animal tracking (DeepLabCut, SLEAP, LEAP, or similar), wants to label training frames, is debugging bad tracking (jumping keypoints, low confidence, identity swaps in multi-animal video), needs kinematic features (speed, distance traveled, joint angles) from existing tracking output, or is building a behavior classifier (freezing, rearing, grooming, social contact) from either tracking output or raw video (e.g. with SimBA, JAABA, or a custom classifier).
1. Choose a tracking tool
| Tool | Best for | Notes |
|---|---|---|
| DeepLabCut (DLC) | Single or multi-animal, most widely adopted, large community model zoo | pip install deeplabcut; GUI or Python API; supports multi-animal (maDLC) with identity tracking |
| SLEAP | Multi-animal, social behavior, fast inference, active development | pip install sleap; strong multi-animal identity tracking and GUI labeling |
| LEAP / Anipose | 3D multi-camera pose | Anipose wraps DLC/SLEAP for calibrated multi-camera 3D reconstruction |
Both DLC and SLEAP are supervised: they need a set of manually labeled frames to train a model for the specific camera angle, lighting and animal/apparatus in use. A model trained on one rig's lighting and camera angle commonly fails on another rig — budget for new labeling, or at least fine-tuning, per rig/condition rather than assuming a published model transfers directly.
2. Label training frames
- Extract a diverse set of frames (DLC's
extract_frames, SLEAP's suggestion-based frame selection) spanning the full range of poses, occlusions, lighting, and (for multi-animal) proximity/overlap conditions expected in the real data — not just easy, well-separated frames. - 100-200 labeled frames is a reasonable starting point for a single animal in a simple arena; complex poses, multiple animals, or variable lighting need substantially more.
- Define keypoints (body parts) that are visible from the camera angle in most frames; a keypoint that is occluded in half the video will have low-confidence, noisy tracking throughout.
- For multi-animal tracking, label identity consistently across frames (which animal is which) since identity-swap errors are the dominant failure mode in social/group video.
3. Train and evaluate
# DeepLabCut: minimal project workflow
import deeplabcut
config_path = deeplabcut.create_new_project(
"MyBehaviorProject", "experimenter", ["/path/to/video1.mp4"],
working_directory="/path/to/project", copy_videos=False,
)
deeplabcut.extract_frames(config_path, mode="automatic", algo="kmeans")
# ... label frames in the GUI: deeplabcut.label_frames(config_path) ...
deeplabcut.create_training_dataset(config_path)
deeplabcut.train_network(config_path, maxiters=100000)
deeplabcut.evaluate_network(config_path, plotting=True)
deeplabcut.analyze_videos(config_path, ["/path/to/new_video.mp4"])
# SLEAP: minimal CLI workflow (after labeling in the SLEAP GUI)
# sleap-train baseline_model.json labels.slp
# sleap-track video.mp4 -m models/baseline_model
import sleap
labels = sleap.load_file("predictions.slp")
Evaluate on a held-out labeled test set before trusting predictions on new video: report pixel error (train vs. test) and inspect the worst-error frames directly, since mean pixel error alone hides systematic failures (e.g. a keypoint that is always correct except during rearing).
4. Clean the raw tracking output
Raw pose estimates from any tracker contain:
- Low-confidence/missing frames: every tool outputs a per-keypoint
confidence (DLC:
likelihood; SLEAP:score). Threshold on it (commonly ~0.6-0.9, tool- and dataset-dependent) and treat below-threshold points as missing rather than using them uncritically. - Jumps: a keypoint teleporting between frames, usually from
low-confidence misdetections. Filter with a median filter, a
velocity/jump threshold, or a Kalman smoother; DLC's companion package
dlc2kinematicsand community tools provide some of this, or implement a simple velocity-threshold interpolation. - Identity swaps (multi-animal): check identity continuity frame to
frame; both DLC (via
tracklets) and SLEAP provide tools to stitch and correct identity assignments after tracking, which generally still need manual review on a sample of swap events. - Missing-data interpolation: short gaps (a few frames) can be linearly interpolated; long gaps (occlusion behind an object) should be left as missing rather than interpolated across, since interpolation invents kinematics that were not observed.
5. Extract kinematic and behavioral features
From cleaned body-part trajectories (in pixels, then converted to real-world units via a calibration — a ruler or checkerboard of known size in the frame, or full camera calibration for Anipose 3D data):
- Locomotion: centroid speed, distance traveled, time in zones (for open-field/place-preference assays), turning angle.
- Posture/kinematics: joint angles (e.g. hip-knee-ankle for gait), body-part distances (e.g. nose-to-tail for stretching/rearing), head direction.
- Events/states: define behavior bouts (freezing, grooming, rearing, social approach) either by hand-crafted thresholds on kinematic features (e.g. freezing = centroid speed below a threshold for at least N consecutive frames) or with a supervised classifier trained on hand-labeled bouts (SimBA, JAABA, B-SOiD for unsupervised discovery of behavioral syllables).
- Always report the frame rate and any temporal smoothing applied before computing speed/acceleration — pose-estimation noise is amplified by differentiation, and under-smoothed speed traces are a common source of spurious "fast" events.
6. Align with neural data
To correlate behavior with simultaneously recorded neural signals, the
camera frame times must be on the same clock as the neural recording: use
a hardware frame-timestamp signal (camera strobe/frame-sync pulse recorded
on an aux channel) rather than assuming a nominal frame rate, following
the same logic as neuro-sync-forensics. A camera's actual frame rate
commonly drifts from its nominal rate (dropped frames, USB bandwidth
limits), which silently misaligns behavior and neural events if not
checked.
7. Quality checks
- Spot-check tracking on representative video clips by overlaying predicted keypoints, including clips the model was not trained or validated on.
- Report the fraction of frames below the confidence threshold per keypoint; a keypoint that is frequently low-confidence needs either a camera-angle change or more targeted labeling, not just a lower threshold.
- For any derived behavior classifier, report precision/recall against a held-out set of hand-scored bouts, not just visual agreement.
Output
A short tracking report: tool and model (or model zoo source), number of training frames and keypoints, train/test pixel error, confidence threshold used and fraction of frames excluded per keypoint, cleaning steps applied (jump filtering, interpolation, identity-swap correction), pixel-to-real-world calibration, and the kinematic/behavioral features extracted with their definitions and thresholds.
Prerequisites
- Video with adequate resolution and frame rate for the behavior of interest (fast movements like whisking or paw kinematics need higher frame rates than general locomotion), and consistent lighting/camera position across sessions if comparing across days.
- GPU strongly recommended for training (DLC/SLEAP both support CPU inference but training on CPU is impractically slow for most datasets).
- A known physical scale in the frame (ruler, checkerboard, or known arena dimensions) to convert pixel coordinates to real-world units.
Limitations
- Pose-estimation models are rig- and condition-specific; accuracy on video that differs from the training distribution (new camera angle, lighting, animal strain/coat color, occluding objects) should not be assumed and must be checked against held-out labeled frames from the new condition.
- This skill produces kinematic and behavioral-event features; it does not itself provide a validated ethogram or behavioral taxonomy — classifier outputs (freezing, rearing, etc.) should be validated against independent human scoring before being treated as ground truth.
- 3D reconstruction from multiple cameras (Anipose or similar) requires a proper multi-camera calibration; skipping calibration and assuming approximate geometry produces systematic distance and angle errors.
示例提示词
帮我用DeepLabCut追踪这段开野实验视频里小鼠的姿态并提取运动特征。
所属插件
安装该插件会一并获得同领域的 45 个 Skill / MCP。
同插件的其他科研 Skill
- Allen脑区本体查询Looks up Allen Institute brain region names, acronyms and atlas hierarchy, and picks a BrainGlobe reference atlas. Use when matching region labels across datasets or papers.
- BIDS神经影像数据管理Converts raw EEG or fMRI data to BIDS, validates with bids-validator, and queries or manages datasets with pybids and datalad. Use when organizing or sharing neuroimaging data.
- Brian2脉冲神经网络仿真Simulates LIF, AdEx and Hodgkin-Huxley spiking neuron networks in Brian2, including STDP plasticity and recurrent dynamics. Use when building a spiking network model.
- 钙成像数据分析Processes two-photon or widefield calcium imaging with Suite2p or CaImAn, from motion correction through ROI extraction to dF/F and spike deconvolution. Use for calcium imaging movies.
- 功能连接组图论分析Computes functional connectivity matrices and graph-theory metrics such as modularity and path length from ROI time series. Use when analyzing brain network topology.
- MNE脑电脑磁分析Runs an MNE-Python EEG or MEG pipeline covering preprocessing, ICA cleanup, ERP and time-frequency analysis, and source localization. Use to analyze raw EEG/MEG recordings end to end.
- 神经解码无泄漏评估Guides leakage-free cross-validation of neural decoders, including subject grouping, nested CV, chance levels and confound checks. Use when training or reporting a BCI classifier.
- 电极通道映射校验Checks that EEG, ECoG or probe channel labels and positions match physiology using correlation-distance consistency. Use when montage labels may be swapped or bridged.
- 聚类置换统计检验Explains how to set up and correctly interpret cluster-based permutation tests and TFCE for ERP or time-frequency data. Use to avoid onset or localization overclaims.
- 神经连接性分析核查Guides choice of leakage-robust connectivity measures such as wPLI, imaginary coherency and AEC, with confound controls. Use when reviewing or planning a connectivity analysis.
- 神经数据集陷阱审查Checklist for auditing neural datasets before training: rate and channel consistency, duplicate subjects, label mapping. Use before modeling on a public or lab dataset.
- 神经数据档案库导航Lists neural data archives such as OpenNeuro, DANDI, PhysioNet and MOABB by paradigm, with access tiers and download guidance. Use when finding a dataset for a research question.
- DBS植入物传感数据分析Loads, time-aligns and analyzes sensing data from DBS and bidirectional implants such as Percept and Summit RC+S. Use with implant LFP exports, packet loss or aDBS biomarkers.
- 神经解码器嵌入式移植Ports a neural signal-processing or BCI decoder from Python or MATLAB to fixed-point embedded C on a microcontroller. Use when moving a decoder onto implant or headstage firmware.
- 神经设备法规合规映射Maps a neurotech device to the regulatory standards and testing it needs and builds a requirements-to-risk traceability matrix. Use when planning verification or a design review.
- EEG预处理流程审查Designs or audits an EEG or MEG preprocessing pipeline in MNE-Python, EEGLAB, FieldTrip or Brainstorm. Use when choosing or reviewing filter, ICA or epoching settings.
- 神经电极电化学表征Characterizes neural electrodes electrochemically via impedance spectroscopy, cyclic voltammetry and charge-injection limits. Use when comparing electrode coatings or charge capacity.
- 神经记录文件格式转换Opens, inspects and converts neural recording files from EEG, MEG, intracranial and fNIRS acquisition systems. Use when a reader errors or units, rates or events look wrong.
- 神经信号基础模型评估Fairly evaluates pretrained EEG or iEEG foundation models against classical baselines with matched data and splits. Use when fine-tuning or linear-probing a pretrained model.
- 神经记录前端电路设计Designs or reviews analog front ends for neural recording headstages, covering noise budget, CMRR and ADC resolution. Use when choosing an amplifier or debugging a noisy front end.
- 脑机解码器长期稳定性Evaluates intracortical BCI decoders across days using zero-shot and few-shot regimes to quantify drift and recalibration cost. Use to assess decoder stability over sessions.
- 植入设备功耗热预算Budgets power, data rate and tissue heating for implanted or wireless neural interfaces against thermal screening limits. Use when sizing a high-channel-count implant design.
- NeuroKit2生理信号处理Processes physiological biosignals such as ECG, EEG, EDA, RSP, EMG and EOG with NeuroKit2, including HRV and complexity metrics. Use for psychophysiology or multi-modal signal analysis.
- NeuroMorpho神经元形态检索Finds and compares digital neuron reconstructions on NeuroMorpho.Org by region, cell type or species and reads their morphometry. Use when real neuron morphologies are needed.
常见问题
动物行为姿态追踪能做什么?
Tracks animal pose and behavior from video with DeepLabCut or SLEAP, and extracts kinematic and behavioral event features. Use for markerless tracking or scoring behavior。
如何安装动物行为姿态追踪?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「动物行为姿态追踪」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
动物行为姿态追踪需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
动物行为姿态追踪经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。