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.
Distribusi Generalized Exponential diperkenalkan oleh Rameshwar D. Gupta dan Debasis Kundu pada tahun 2007. Distribusi Generalized Exponential tersebut merupakan hasil generalized distribusi Exponential. Skripsi ini menjelaskan distribusi Generalized Exponential Marshall Olkin yang merupakan hasil dari perluasan distribusi Generalized Exponential menggunakan metode Marshall Olkin. Distribusi Generalized Exponential Marshall Olkin lebih fleksibel dari distribusi sebelumnya terutama pada fungsi hazardnya yang memiliki berbagai bentuk baik monoton (naik atau turun) maupun non monoton (bathub atau upside down bathup) sehingga dapat memodelkan data survival dengan lebih baik. Sifat fleksibelitas ini disebabkan karena penambahan parameter baru ke dalam distribusi Generalized Exponential. Selanjutnya dijelaskan beberapa karakteristik dari distribusi Generalized Exponential Marshall Olkin antara lain fungsi kepadatan peluang (fkp), fungsi distribusi kumulatif, fungsi hazard, momen ke-n, mean, dan variansi. Penaksiran parameter dilakukan dengan metode maximum likehood. Pada bagian aplikasi ditunjukkan data survival yang berasal dari data Aarset (1987) berdistribusi Generalized Exponential Marshall Olkin. Selanjutnya distribusi Generalized Exponential Marshall Olkin dibandingkan dengan distribusi Alpha Power Weibull untuk mencari distribusi mana yang lebih cocok dalam memodelkan data Aarset (1987). Dengan menggunakan AIC dan BIC distribusi Generalized Exponential Marshall Olkin lebih cocok dalam memodelkan data Aarset (1987).
Generalized Exponential distribution was introduced by Rameshwar D. Gupta and Debasis Kundu in 2007. Generalized Exponential distribution was generated by generalized transformation of the Exponential distribution. This thesis explained the Generalized Exponential Marshall-Olkin distribution which is the result of the expansion of the Generalized Exponential distribution using the Marshall-Olkin method. The Generalized Exponential Marshall-Olkin distribution has a more flexible form than the previous distribution, especially in its hazard function which has various forms that it can represent survival data better. The flexibility characteristic is due to the addition of new parameters to the Generalized Exponential distribution. Futhermore, some characteristics of the Generalized Exponential Marshall-Olkin distribution was explained such as, the probability density function(PDF), cumulative distribution function, survival function, hazard function, moment, mean, and variance. Parameter estimation was conducted by using the maximum likelihood method. In the application section was shown survival data from Aarset data (1987) which distributed Generalized Exponential Marshall-Olkin distribution. Futhermore, Generalized Exponential Marshall-Olkin distribution was compared with Alpha Power Weibull disstribution to decided theprominent distribution in modeling Aarset data (1987). Using AIC and BIC, Generalized Exponential Marshall-Olkin distribution more suitable in modeling Aarset data (1987).