I already have a working Python pipeline that watches a live game feed, runs it through YOLO to carve out short MP4 snippets, and pushes those clips to a monitor in real time. A Flutter front-end then lets fans pull either single clips or concatenated highlight reels to their iPhone or Android devices. In addition, the Yolo feed provides information for other performance calculations that post under each snippet on the monitor. Two pain points are slowing us down: 1. YOLO interference Right now one key smaller object interferes with other objects that are detected because there is no prioritization layer in place. This causes some of the performance calculations to be intermittent resulting in some incomplete calculations. I need logic that decides, on the fly, which detection wins when classes conflict—whether that means tweaking NMS thresholds, adding a class-confidence hierarchy, or inserting a lightweight post-processor in Python/C++ that still keeps frame-rate latency low. 2. Flutter connection hiccups The mobile app fails to connect to the WiFi hotspot or drops its link to the snippets/concatenated videos. A rock-solid fix that works across iOS and Android is required so a user can tap once and reliably receive either a single clip or a stitched highlight. Immediate deliverables • Implement and benchmark an object-priority solution inside the existing YOLO workflow. • Patch the Flutter download pipeline so it maintains a stable connection and reports clear progress to the user. • Provide clean, documented code and a short read-me that lets me replicate your results. This project will keep evolving—containerization for production, additional model tuning, GPU scaling, UI polish including animation—so I’m looking for a team comfortable taking on long-term, performance-critical work. If you’ve handled real-time video with YOLO, FFMPEG/GStreamer, and Flutter before, I’d love to see how you’d approach these first fixes. An NDA will be needed.