Multi object tracking is one of the most important topics of computer science that has many applications, such as surveillance system, navigation robot, sports analysis, autonomous driving car, and others. One of the main problems of multi-object tracking is occlusion. Occlusion is an object that is covered by other objects. Occlusion may cause the ID between objects to be switched. This study discusses occlusion on multi-object tracking and its completion with network flow. Given objects detection on each frame, the task of multi object tracking is to estimate the movement of objects and then connect the estimation objects corresponding to the objects in the next frame or well known as the data association. Notice that each object on a frame as a node, then there is an edge connecting each node on a frame with other frames, this architecture in graph theory is known as network flow. Then find the set of edges that provide the greatest probaility of transition from one frame to the next, or to the optimization problem well known as max-cost network flow. Edge contains information on how probabiltity a node moves to the node in the frame afterwards. This probability calculation is based on position distance and similarity feature between frames, the feature used is CNN feature. We modeled max-cost network flow as the maximum likelihood problem which was then solved with the Hungarian algorithm. The data used in this research is 2DMOT2015. Performance evaluation results show that the system built gives accuracy 20.1% with the ID switch is 3084 and fast computational process on 215.8 frame/second.
"Di era sekarang ini, informasi telah menjadi kebutuhan yang sangat penting bagi organisasi. Untuk memperoleh informasi yang bermanfaat, data sebagai sumber informasi harus memiliki kualitas yang baik. Salah satu organisasi yang saat ini bergantung pada kualitas informasi adalah PT. Bank Negara Indonesia, Tbk (BNI). BNI dalam usahanya melakukan transformasi bisnis menjadi bank yang berorientasi pada pelanggan melalui BNI Reformasi, sangat bergantung pada kualitas data nasabah yang baik. Kualitas data yang baik didapatkan dari pengelolaan data yang baik, termasuk diantaranya adalah pengukuran dan peningkatan kualitas data.
Penelitian ini dilakukan untuk mengukur tingkat kematangan dari pengelolaan kualitas data dan memberikan rekomendasi peningkatan kualitas data berdasarkan Data Quality Framework dari David Loshin dan Data Management Body of Knowledge (DMBOK) dari DAMA Institute.
Kerangka kerja yang lengkap dimiliki oleh Data Quality Framework sehingga dapat dihasilkan tingkat kematangan kualitas data yang dimiliki BNI untuk domain harapan, dimensi kualitas data, kebijakan, prosedur, tata kelola, standar, teknologi, dan pengukuran kinerja. Berdasarkan tingkat kematangan dan harapanharapan dari BNI, penulis menentukan kesenjangan yang digunakan untuk meningkatkan kematangan kualitas data di BNI. Berdasarkan best practice dan kerangka kerja yang ada di DMBOK, berhasil didapatkan rekomendasi peningkatan kualitas data, yaitu: perbaikan terhadap data quality requirements, menetapkan dan mengevaluasi data quality service levels, memantau prosedur operasional dan kinerja data quality management, serta melakukan pembersihan dan perbaikan data.
In this era, information has become critical for organization. To gain a maximum benefit from information, data as a source for information must have a good quality. PT. Bank Negara Indonesia (BNI) is one of organization that depends on good information quality. BNI is on their way to transforming from product centric to customer centric, they called this transformation as BNI Reformed. This transformation success is depends on their good customer data quality. Good data quality obtained from well data management, including the measurement and improvement of data quality.
This research was conducted to measure the maturity level of data quality management and provide recommendations on data quality improvement based Data Quality Framework from David Loshin and Data Management Body of Knowledge (DMBOK) of DAMA Institute.
Data Quality Framework has complete framework so that the maturity level of data quality in BNI can be measured for each domain: expectations, the data quality dimensions, policies, procedures, governance, standards, technology, and
performance measurement. Based on the level of maturity and expectations of BNI, the authors determine the gaps that are used to improve data quality maturity in BNI. Based on best practices and frameworks that exist in DMBOK, we can get data quality improvement recommendations, namely: improvements to data quality requirements, define and evaluate the data quality service levels,operational procedures and monitoring the performance of data quality management, as well as cleaning and repair data."