[{"data":1,"prerenderedAt":247},["ShallowReactive",2],{"project-21462993":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":39,"post_text":42,"what":43,"said":71,"maker_in_thread":144,"shape":151,"grid":154,"attempts":206,"same_week":211,"maker_shows":31,"maker_hidden":239,"reader_version":240,"card":241},"21462993","multi-object-tracker","OpenCV based multi-object-tracker with various object detection models","title","Show HN: OpenCV based multi-object-tracker with various object detection models","https:\u002F\u002Fgithub.com\u002Fadipandas\u002Fmulti-object-tracker","github.com","adipandas",1573051162,2019,105,21,466,2195,22,"notable","ai","object tracking","library",[21,24,25,26,27],"opencv","object detection","multi-object tracking","pretrained models","curious",-0.107,{"positive":31,"neutral":32,"mixed":33,"critical":31},1,6,0,8,{"idea":36,"performance":37,"execution":38},{"positive":31,"critical":31},{"positive":33,"critical":33},{"positive":33,"critical":33},[40,40,33,33,41,33,33,33,40,33,40,33,40,33,40,33,33,33,33,31,33],3,5,null,{"problem":42,"audience":42,"pricing":42,"motivation":44,"time_to_build":42,"stack":51,"openness":69,"stage":70,"team_size":70},{"value":45,"source":46,"evidence":47},"Built as a fun project and shared the work","maker",[48],{"id":49,"by":11,"text":50},"21464223","Okay, I am not sure about others. But I was working on this as a fun project. And I wanted to share my work. Hope you find it useful and please let me know your suggestions and…",[52,58,62],{"value":53,"source":46,"evidence":54},"OpenCV",[55],{"id":56,"by":11,"text":57},"21464427","@mendeza, Thank you for the feedback. I am planning to add detectron models as well to this repository. Initial intention of this project was to avoid direct dependency of any…",{"value":59,"source":46,"evidence":60},"Pretrained object detection models (no deep learning framework dependency)",[61],{"id":56,"by":11,"text":57},{"value":63,"source":64,"evidence":65},"PyTorch","commenter",[66],{"id":67,"by":11,"text":68},"21464792","Pytorch makes it even more fun.","open_source","unknown",{"praise":72,"objections":84,"requests":99,"questions":119,"alternatives":124},[73],{"value":74,"source":64,"evidence":75},"Useful tracking resources and pyimagesearch tutorials recommended",[76,80],{"id":77,"by":78,"text":79},"21466030","nullbyte","PyImageSearch is a fantastic resource for learning this stuff. Highly recommend it.",{"id":81,"by":82,"text":83},"21467516","alexcnwy","I've built several object detection systems and you definitely want to fine-tune your model to get good results, even if the object class you want to track is available in a…",[85,92],{"value":86,"source":64,"evidence":87},"Thousands of similar object detection repositories already exist",[88],{"id":89,"by":90,"text":91},"21464113","binarysaurus","There arw thousands of these repositories all over the place...",{"value":93,"source":64,"evidence":94},"IOU-based tracking may fail under significant obstructions",[95],{"id":96,"by":97,"text":98},"21464290","martinshen","Have you tried using object attributes\u002Ffeatures to enable tracking instead of IOU-based tracking? I suspect this tracker falls apart when there are significant obstructions.…",[100,107,114],{"value":101,"source":64,"evidence":102},"Add Detectron 2 support",[103],{"id":104,"by":105,"text":106},"21464251","mendeza","I work a lot with object detection at my current role. Would be cool to add Detectron 2, seems that this library that has some of the state of the art(SOTA) models in object…",{"value":108,"source":64,"evidence":109},"Add TF Object Detection API support",[110,111],{"id":104,"by":105,"text":106},{"id":112,"by":105,"text":113},"21467143","It would be great if your tool integrates popular object detection frameworks such as TF Object Detection API. Would save people a lot of headache installing and configuring in…",{"value":115,"source":64,"evidence":116},"Build a data labeling and fine-tuning tool",[117,118],{"id":104,"by":105,"text":106},{"id":56,"by":11,"text":57},[120],{"value":121,"source":64,"evidence":122},"Whether attribute\u002Ffeature-based tracking could replace IOU-based tracking",[123],{"id":96,"by":97,"text":98},[125,132,136,140],{"value":126,"source":64,"evidence":127},"Label Studio for labeling and fine-tuning object detection models",[128],{"id":129,"by":130,"text":131},"21466722","deppp","Check out our open-source tool called Label Studio, https:\u002F\u002Flabelstud.io and we have a commercial offering that does exactly this, finetuning the models.",{"value":133,"source":64,"evidence":134},"TF Object Detection API",[135],{"id":104,"by":105,"text":106},{"value":137,"source":64,"evidence":138},"Detectron 2",[139],{"id":104,"by":105,"text":106},{"value":141,"source":64,"evidence":142},"DeepSORT",[143],{"id":96,"by":97,"text":98},{"comments":32,"answered":31,"key":145},[146,147,148],{"id":56,"text":57},{"id":67,"text":68},{"id":149,"text":150},"21469637","The top-down view problem is what I was facing when I was trying to use a detection model for a project with quadcopters. For this I had to train my object detector with the data…",{"commenters":152,"max_depth":40,"maker_replies":32,"first_comment_mins":153,"lifespan_hours":152},11,109,[155,157,159,163,165,168,172,173,174,175,178,180,182,185,188,191,194,196,200,202,204],[104,33,40,156,105,33],"project\u002Fneutral\u002Fidea",[158,33,40,156,105,33],"21464315",[160,33,33,161,162,33],"21464372","commenter\u002Fneutral\u002Fnone","inetknght",[56,33,33,164,11,31],"maker\u002Fpositive\u002Fidea",[166,33,41,167,105,33],"21467119","project\u002Fpositive\u002Fidea",[169,33,33,170,171,33],"21464686","other\u002Fneutral\u002Fnone","ganeshkrishnan",[67,33,33,170,11,31],[129,33,33,170,130,33],[112,33,40,156,105,33],[176,33,33,177,105,33],"21468413","commenter\u002Fpositive\u002Fnone",[81,31,40,179,82,33],"project\u002Fneutral\u002Fperformance",[149,31,33,181,11,31],"maker\u002Fneutral\u002Fperformance",[96,183,40,184,97,33],2,"project\u002Fneutral\u002Fexecution",[186,183,33,187,11,31],"21464500","maker\u002Fneutral\u002Fexecution",[189,183,40,184,190,33],"21465439","kevinsundar",[192,183,33,193,11,31],"21468722","commenter\u002Fneutral\u002Fexecution",[77,40,33,195,78,33],"other\u002Fpositive\u002Fdocs",[197,198,33,170,199,33],"21466627",4,"mbpqd",[201,198,33,170,105,33],"21467078",[89,41,31,203,90,33],"project\u002Fcritical\u002Fidea",[49,41,33,205,11,31],"maker\u002Fneutral\u002Fnone",[207,210],{"id":208,"t":209,"points":31,"comments":33},"20989153",1568672647,{"id":4,"t":12,"points":14,"comments":15},[212,217,221,226,231,235],{"id":213,"name":214,"points":215,"category":216},"21417965","Simplescraper",332,"dev_tools",{"id":218,"name":219,"points":220,"category":216},"21439918","Tailwind Builder",295,{"id":222,"name":223,"points":224,"category":225},"21461701","microvm",145,"infrastructure",{"id":227,"name":228,"points":229,"category":230},"21418882","HR code",124,"languages",{"id":232,"name":233,"points":234,"category":225},"21423612","kubeadm-playbook",122,{"id":236,"name":237,"points":238,"category":230},"21427363","Domino",116,false,"v2",{"id":242,"name":5,"line":6,"ai":239,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":243,"top":18,"kw":244,"maker":11,"domain":10,"tier":19,"attempts":183,"strip":245,"url":9,"mix":246,"praise":74,"objection":86,"sub":21},21462993,-0.11,[21,24,25,26,27],"330050003030303000010",[31,32,33,31],1794036582688]