Update app.py

app.py

@@ -111,46 +111,12 @@ Task Context:
 You are analyzing video footage from Step {step_number} of a tire manufacturing process where a delay has been detected. Your task is to determine the most likely cause of the delay from the following possible reasons:
 {', '.join(possible_reasons)}
 Required Analysis:
- Carefully observe the video for visual cues indicating production interruption.Analyse frames and contours around the object.
+ Carefully observe the video for visual cues indicating production interruption.Analyse frames and contours around the objects: 'h-stock_left','h-stock_right','conveyor1','conveyor2','compressor_metal','person','orange_roller_metal_left','orange_roller_metal_right','white_down_roller_left','white_down_roller_right','vaccum_blue'.
  If no person is visible in any of the frames, the reason probably might be due to his absence.
  If a person is visible in the video and is observed touching and modifying the layers of the tire, it means there is a issue with tyre being patched hence he is repatching it.
  Compare observed evidence against each possible delay reason.
  Select the most likely reason based on visual evidence.
 
- 1. Contour Detection and Annotation
-Detect contours around machinery and objects in each frame using OpenCV.
-Assign specific contours to different manufacturing steps (e.g., bead placement machine, ply machine).
-Label contours with the corresponding manufacturing step (e.g., Step 1: Bead Insertion).
-2. Time Analysis for Each Step
-Extract timestamps for when objects (e.g., beads, inner liner, ply) enter and exit the area of interest for each step.
-Measure the duration spent in each step by comparing these timestamps.
-3. Standard Time Validation
-Compare the observed duration against the standard times provided for each step.
-Highlight steps where the duration exceeds the standard time.
-4. Delay Diagnostics
-For steps exceeding the standard time, log potential causes based on specific analyses:
-Bead Insertion: Detect missing beads or pauses in technician/machine movement.
-Inner Liner Apply: Observe for manual adjustments indicating alignment issues.
-Ply1 Apply: Track object positioning and machine alignment changes.
-Bead Set: Monitor bead alignment and machine operation pauses.
-Turnup: Look for interruptions in material application.
-Sidewall Apply & Stitching: Check for excessive handling or speed fluctuations.
-Carcass Unload: Track technician presence and delays in object removal.
-5. Trajectory and Movement Analysis
-Use object tracking algorithms to monitor the movement of objects and machinery across frames.
-Correlate motion paths with the expected operational flow of each step to identify inefficiencies or anomalies.
-6. Visualization
-Annotate frames with contours, timestamps, and detected delays for each step.
-Save annotated videos for further review.
-Generate summary charts showing step-wise delays, bottlenecks, and technician involvement.
-7. Output Reports
-Provide a detailed log of delays with root-cause suggestions for each step.
-Include metrics like:
-Total delays per step.
-Percentage of delays exceeding the standard time.
-Frequency of technician or machine interventions.
-
-
 Please provide your analysis in the following format:
 1. Selected Reason: [State the most likely reason from the given options]
 2. Visual Evidence: [Describe specific visual cues that support your selection]
@@ -160,6 +126,7 @@ Please provide your analysis in the following format:
 Important: Base your analysis solely on visual evidence from the video. Focus on concrete, observable details rather than assumptions. Clearly state if no person or specific activity is observed."""
 
 
+
 # Load model globally
 model, tokenizer = load_model()