report update

A8/A8_Report.ipynb

@@ -6,38 +6,22 @@
    "metadata": {},
    "source": [
     "\n",
-    "# A8 Report - Pose Estimation System\n",
-    "\n",
-    "**Course sprint deliverable:** A8 notebook documenting installation, usage, software changes, data formats, and results for the MoveNet-based pose estimation pipeline.\n",
-    "\n",
-    "**Prepared for:** Sprint 8 group project  \n",
-    "**Primary references:** `A8/pose_estimator.py`, `A8/keypoint_extractor.py` API target, sample images `test_person.jpg` and `test_person_annotated.jpg`\n",
+    "# A8 Report\n",
     "\n",
     "---\n",
     "\n",
     "## Introduction & Objectives\n",
     "\n",
-    "This notebook documents the current pose estimation system, how to install and run it, the main architectural decisions, and the data formats used to export extracted keypoints.\n",
-    "\n",
-    "### Objectives\n",
-    "- Provide a reproducible environment setup.\n",
-    "- Explain the MoveNet pose estimation library and how it is integrated.\n",
-    "- Walk through the current code and highlight the software changes added by the team.\n",
-    "- Show executable usage examples for image and video processing.\n",
-    "- Document CSV and JSON output schemas.\n",
-    "- Visualize extraction results and sample output data.\n",
-    "- Summarize the system status and next implementation steps.\n",
+    "This notebook documents the current pose estimation system, how to install and run it, the main architectural decisions, and the data formats used.\n",
     "\n",
-    "### Scope of the documented system\n",
+    "### Pose estimator\n",
     "The uploaded `pose_estimator.py` module already provides:\n",
     "- MoveNet model loading from TensorFlow Hub\n",
     "- Image preprocessing\n",
     "- Single-image pose detection\n",
     "- Video frame-by-frame pose extraction\n",
     "- Skeleton overlay rendering\n",
-    "- CLI entry points for image, video, and webcam usage\n",
-    "\n",
-    "This report also includes a lightweight compatibility wrapper for the expected `KeypointExtractor` API so the notebook examples can be run in a consistent way once dependencies are installed.\n"
+    "- CLI entry points for image, video, and webcam usage\n"
    ]
   },
   {
@@ -48,21 +32,6 @@
     "\n",
     "## Environment Setup & Installation\n",
     "\n",
-    "### Supported environment\n",
-    "- **Python:** 3.10 or 3.11 recommended\n",
-    "- **OS:** Windows, macOS, or Linux\n",
-    "- **Hardware:** CPU works; GPU is optional and can improve TensorFlow inference speed\n",
-    "\n",
-    "### Required dependencies\n",
-    "| Package | Recommended version | Purpose |\n",
-    "|---|---:|---|\n",
-    "| tensorflow | `>=2.13,<3.0` | Core deep learning runtime |\n",
-    "| tensorflow-hub | `>=0.16` | Loads MoveNet model from TF Hub |\n",
-    "| opencv-python | `>=4.8` | Image/video I/O and drawing |\n",
-    "| numpy | `>=1.24` | Array operations |\n",
-    "| pandas | `>=2.0` | CSV/JSON export and tabular inspection |\n",
-    "| matplotlib | `>=3.7` | Notebook plotting and visualization |\n",
-    "\n",
     "### Installation steps\n",
     "\n",
     "#### 1. Create and activate a virtual environment\n",
@@ -93,13 +62,7 @@
     "#### 4. Verify installation\n",
     "```bash\n",
     "python -c \"import tensorflow as tf; import tensorflow_hub as hub; import cv2; import numpy; import pandas; print(tf.__version__)\"\n",
-    "```\n",
-    "\n",
-    "### Troubleshooting notes\n",
-    "- If TensorFlow fails to install, check that the Python version is supported by the selected TensorFlow release.\n",
-    "- On Apple Silicon, use a Python/TensorFlow combination that is explicitly supported by the installed wheel.\n",
-    "- If OpenCV video codecs fail, test image mode first and then verify codec support for local MP4 files.\n",
-    "- The first MoveNet load may take longer because TensorFlow Hub downloads and caches the model.\n"
+    "```"
    ]
   },
   {
@@ -162,7 +125,7 @@
     "\n",
     "## Pose Estimation Library Overview\n",
     "\n",
-    "### Why MoveNet?\n",
+    "### MoveNet\n",
     "MoveNet is a lightweight single-person pose estimation model distributed through TensorFlow Hub. It outputs **17 COCO keypoints**, each with:\n",
     "\n",
     "- `x`: normalized horizontal coordinate in the range `[0, 1]`\n",
@@ -177,7 +140,7 @@
     "| `lightning` | 192 x 192 | Faster inference, slightly lower accuracy |\n",
     "| `thunder` | 256 x 256 | Slower inference, higher accuracy |\n",
     "\n",
-    "### Keypoints used\n",
+    "### COCO keypoints\n",
     "The code defines the standard 17 COCO keypoints:\n",
     "\n",
     "`nose, left_eye, right_eye, left_ear, right_ear, left_shoulder, right_shoulder, left_elbow, right_elbow, left_wrist, right_wrist, left_hip, right_hip, left_knee, right_knee, left_ankle, right_ankle`\n",
@@ -205,7 +168,6 @@
     "## Code Walkthrough & Changes\n",
     "\n",
     "### Module structure\n",
-    "The uploaded module is centered on a single class:\n",
     "\n",
     "- `MoveNetPoseEstimator`\n",
     "  - model loading\n",
@@ -243,19 +205,7 @@
     "4. **Video processing pipeline**\n",
     "   - Reads video frame-by-frame, runs inference, stores per-frame results, and optionally writes an annotated MP4.\n",
     "5. **CLI support**\n",
-    "   - Adds `--image`, `--video`, `--webcam`, `--output`, and model selection flags for local testing.\n",
-    "\n",
-    "### Suggested wrapper for the expected issue API\n",
-    "The issue description expects:\n",
-    "\n",
-    "```python\n",
-    "from keypoint_extractor import KeypointExtractor\n",
-    "extractor = KeypointExtractor(model='movenet')\n",
-    "keypoints = extractor.extract_from_video('video.mp4')\n",
-    "extractor.save_to_csv(keypoints, 'output.csv')\n",
-    "```\n",
-    "\n",
-    "The next cell implements a notebook-local compatibility wrapper with that API. This keeps the report executable even if `keypoint_extractor.py` has not yet been committed locally.\n"
+    "   - Adds `--image`, `--video`, `--webcam`, `--output`, and model selection flags for local testing.\n"
    ]
   },
   {
@@ -802,40 +752,6 @@
     "plt.tight_layout()\n",
     "plt.show()\n"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7309d3d4",
-   "metadata": {},
-   "source": [
-    "\n",
-    "## Conclusions\n",
-    "\n",
-    "### What is complete in this report\n",
-    "- The notebook includes all requested A8 sections.\n",
-    "- Installation steps are documented and reproducible.\n",
-    "- The current `pose_estimator.py` architecture is described.\n",
-    "- The expected `KeypointExtractor` API is documented and supported by a notebook-local compatibility wrapper.\n",
-    "- CSV and JSON output formats are documented with examples.\n",
-    "- Visualization examples compare input and skeleton overlay output.\n",
-    "\n",
-    "### Recommended follow-up commit items\n",
-    "1. Add a project-level `requirements.txt` or `environment.yml`.\n",
-    "2. Commit `keypoint_extractor.py` as a thin wrapper around `MoveNetPoseEstimator`.\n",
-    "3. Add one short sample video or test clip for reproducible notebook demonstration.\n",
-    "4. Add automated tests for:\n",
-    "   - image inference return structure\n",
-    "   - CSV export schema\n",
-    "   - JSON export schema\n",
-    "   - invalid file path handling\n",
-    "\n",
-    "### Acceptance criteria check\n",
-    "- **Complete A8 notebook with all sections:** yes\n",
-    "- **Installation reproducible from documentation:** yes\n",
-    "- **Code examples executable in notebook:** yes, once the documented dependencies are installed\n",
-    "- **Data formats clearly documented:** yes\n",
-    "- **Visualizations demonstrate working system:** yes\n"
-   ]
   }
  ],
  "metadata": {