Tracking Human Motions In Photographing:A Context Aware Energy-Saving Scheme For Smart Phones

Due to the portability of smart phones,more and more people tend to take photos with smart phones.However,energy-saving continues to be a thorny problem,since photographing is a rather power hungry function and the development of the battery isn't as good as the other hardwares of the smartphone.Through our observation,dur-ing the process of photographing,a lot of energy is wasted in preparations before shoot-ing.At the same time,we have found several energy-saving points.Therefore,we can sense user's activities and make use of appropriate energy-saving points to re-duce energy consumption.In order to extend the battery life of the phones while taking photos,we propose a context aware energy-saving scheme "SenSave".SenSave senses the user's activities during photographing and adopts suitable energy-saving strategies accordingly.By leveraging the low power-consuming embedded sensors like linear accelerometer,gravity sensor and gyroscope,we can extract representative features to recognize the user,s activities and reduce unnecessary energy consumption.Besides,by maintaining an activity state machine,SenSave can determine the user's activity pro-gressively and improve the recognition accuracy.Additionally,we enhance "SenSave"by introducing an extended Markov chain to predict the next activity state and adjust the energy-saving strategy in advance.At last,we develop the corresponding application for the android os based smartphones and verify the efficiency of out application in the real environment.The main innovative achievements are as follows:·First,we propose a context aware energy-saving scheme for smart camera phones,by leveraging the built-in sensors for activity sensing.Based on the activity recog-nition results,we can make corresponding energy-saving strategies.·Second,we build a three-level architecture for activity sensing,including body level,arm level and wrist level.We use the low power-consuming sensors like the accelerometer,gravity sensor and gyroscope to extract representative features to distinguish one activity from another.By maintaining an activity state machine,we can determine the user activity progressively and reduce the error of activity recognition.·Third,we design an efficient energy-saving scheme,which can adaptively adopt a suitable energy-saving strategy without user interaction,according to the activity states.Besides,we also introduce an extended Markov chain to predict the next activity state,in order to adopt a suitable strategy in advance for further energy saving.·Fourth,we have implemented a system prototype in android-powered smart cam-era phones.The experiment results shows that our solution is able to recognize the user's activities with an average accuracy of 95.5%.Besides,wen can reduce the overall energy consumption by 46.5%,when compared to the approach with-out using energy-saving strategies.By introducing the extended Markov chain,we can reduce additional energy by 6.4%.