Eliminate redundant JPEG frame loading via shared frame store

chore(yolo11): update yolo naming comments

refactor: rename hf_yolov8 → yolo11 across codebase

feat(segmentation): add YSAM2 variants and mission-aware detector mapping

chore: remove dead code and unused frontend modules

refactor(gsam2): make SAM2 detector-agnostic

perf: increase production keyframe step from 20 to 60

feat: expose num_maskmem parameter in benchmark profile/analysis endpoints

feat: add benchmark profiler & roofline analysis system

feat(frontend): improve UI for detection and chat interaction

feat(backend): enhance inference pipeline with GLM logic and structured outputs

Handle GPT refusal paths and preserve assessment status

Refine Grounded-SAM2 tracking behavior and video frame handling

Remove SAM3 and standardize segmentation on Grounded-SAM2

Add diagnostic logging to pinpoint tracker dropping detections

Fix Grounding DINO detections dropped by ByteTracker threshold mismatch

Refine GPT enrichment logic, add relevance badges to UI, and fix minor model/logging issues

Add StreamingVideoWriter (ffmpeg pipe), reuse first-frame GPT results in inference pipeline

GPT reasoning: add in-memory frame encoding, image_b64 support, use gpt-4o-mini for relevance

Refactor ByteTracker: add min_hits confirmation, split thresholds, associate unconfirmed tracks

Tune ByteTracker: lower track_thresh to 0.3, increase track_buffer to 60

Add vision-grounded mission parsing: send first frame to GPT for object class refinement

Update overlays, tracker, GPT reasoning, and threat chat improvements

feat: Add LLM post-processing relevance gate for broad detection

feat: Add mission-driven object relevance abstractions

fix: Remove chat emojis, improve tracker GPT metadata sync

feat: Add threat chat feature for Q&A about detected threats

feat(threat-assessment): implement naval threat analysis with GPT-4o\n\n- Rename utils/gpt_distance.py to utils/gpt_reasoning.py and update logic for 15 naval threat features\n- Add Pydantic schemas for NavalThreatAssessment in utils/schemas.py\n- Update backend (app.py, inference.py) to use new threat estimation and pass full metadata\n- refactor(frontend): render threat level badges and detailed feature table in UI

Fix: IndexError in ByteTracker

feat: replace SimpleTracker with ByteTrack

Add granular logging for frame processing and ffmpeg

fix: Switch to gpt-4o-mini and verified queue safety

feat: Implement SAHI Tiling for 4K video detection

feat: Implement AsyncVideoReader for parallel video decoding

fix: Handle empty GPT responses and log outputs

Feature: GPT distance integration, Radar Map, and optional legacy depth

update:inference pipeline optimization

inital commit