Tracking Human Motions in Photographing 29:3 the same settings(e.g.,the same preview size),which result in comparable energy consumption to that of shooting photos.If we can recognize the user's activity and detect the duration between two consecutive shots,then we can decrease the screen brightness,preview size,or the preview frame rate to reduce energy cost. In this article,by leveraging activity sensing,we propose a context-aware energy-saving scheme for smart camera phones.Our idea works based on the observation that most smart phones are equipped with low power-consuming sensors,such as the accelerometer and gyroscope.We can leverage these tiny sensors to recognize the user's activities,such that the corresponding energy- saving strategies (e.g,decreasing the screen brightness,decreasing the frame rate,etc.)can be applied.To reduce the error of activity recognition,we maintain an activity state machine to de- termine the activity state progressively.In addition,we also introduce an extended Markov chain to predict the next activity state,to adopt a suitable energy-saving strategy in advance to fur- ther reduce energy cost.Without user interaction,we can reduce the energy consumption during photographing while guaranteeing a good user experience. 1.4 Technique Challenges and Solutions There are some challenges in activity sensing and designing the energy-saving scheme for taking photos with smart phones. -Activity sensing:The first challenge is how to use the sensor data for activity recognition. To address this challenge,we propose a three-level architecture,which classifies the activi- ties into three levels:body level,arm level,and wrist level.For the sensor data of a potential activity,we first utilize the variance and periodicity of the sensor data to classify the activity into one of the three levels.For activities in the same level,we combine data from differ- ent sensors to distinguish one from another based on the features of activities.To reduce the error of activity recognition,we maintain an activity state machine and determine the user's activity state progressively. -Energy-saving scheme design:The second challenge is how to design an appropriate energy-saving scheme with the recognized activities during photographing.To address this challenge,we propose a context-aware energy-saving scheme SenSave,which adopts suit- able energy-saving strategies based on the user's activities.In body level,SenSave focuses on turning ON/OFF sensors,camera,and screen.In arm level,SenSave focuses on adjust- ing the screen brightness,starting or stopping the camera preview.In wrist level,SenSave focuses on adjusting the preview size,the preview frame rate of the camera.In each level, we will adjust the parameters in an energy-saving strategy for the specific activity. -Trade-off between activity sensing and energy saving:The third challenge is how to make an appropriate trade-off between the accuracy of activity sensing and energy con- sumption.Obviously,more types of sensor data and larger sampling rates contribute to higher accuracy of activity sensing,while resulting in more energy consumption.To ad- dress this challenge,we only leverage the low power-consuming sensors like accelerom- eter and gyroscope for activity recognition.When guaranteeing the recognition accuracy, we choose the sampling rates of sensors as small as possible.For further energy saving,we introduce an extended Markov chain to predict the next activity state and adopt the suitable energy-saving strategy in advance. 1.5 Key Contributions We make the following contributions in this article(a preliminary version of this work appeared in Fan et al.(2015)). ACM Transactions on Sensor Networks,Vol.13,No.4,Article 29.Publication date:September 2017.Tracking Human Motions in Photographing 29:3 the same settings (e.g., the same preview size), which result in comparable energy consumption to that of shooting photos. If we can recognize the user’s activity and detect the duration between two consecutive shots, then we can decrease the screen brightness, preview size, or the preview frame rate to reduce energy cost. In this article, by leveraging activity sensing, we propose a context-aware energy-saving scheme for smart camera phones. Our idea works based on the observation that most smart phones are equipped with low power-consuming sensors, such as the accelerometer and gyroscope. We can leverage these tiny sensors to recognize the user’s activities, such that the corresponding energy￾saving strategies (e.g., decreasing the screen brightness, decreasing the frame rate, etc.) can be applied. To reduce the error of activity recognition, we maintain an activity state machine to de￾termine the activity state progressively. In addition, we also introduce an extended Markov chain to predict the next activity state, to adopt a suitable energy-saving strategy in advance to fur￾ther reduce energy cost. Without user interaction, we can reduce the energy consumption during photographing while guaranteeing a good user experience. 1.4 Technique Challenges and Solutions There are some challenges in activity sensing and designing the energy-saving scheme for taking photos with smart phones. —Activity sensing: The first challenge is how to use the sensor data for activity recognition. To address this challenge, we propose a three-level architecture, which classifies the activi￾ties into three levels: body level, arm level, and wrist level. For the sensor data of a potential activity, we first utilize the variance and periodicity of the sensor data to classify the activity into one of the three levels. For activities in the same level, we combine data from differ￾ent sensors to distinguish one from another based on the features of activities. To reduce the error of activity recognition, we maintain an activity state machine and determine the user’s activity state progressively. —Energy-saving scheme design: The second challenge is how to design an appropriate energy-saving scheme with the recognized activities during photographing. To address this challenge, we propose a context-aware energy-saving scheme SenSave, which adopts suit￾able energy-saving strategies based on the user’s activities. In body level, SenSave focuses on turning ON/OFF sensors, camera, and screen. In arm level, SenSave focuses on adjust￾ing the screen brightness, starting or stopping the camera preview. In wrist level, SenSave focuses on adjusting the preview size, the preview frame rate of the camera. In each level, we will adjust the parameters in an energy-saving strategy for the specific activity. —Trade-off between activity sensing and energy saving: The third challenge is how to make an appropriate trade-off between the accuracy of activity sensing and energy con￾sumption. Obviously, more types of sensor data and larger sampling rates contribute to higher accuracy of activity sensing, while resulting in more energy consumption. To ad￾dress this challenge, we only leverage the low power-consuming sensors like accelerom￾eter and gyroscope for activity recognition. When guaranteeing the recognition accuracy, we choose the sampling rates of sensors as small as possible. For further energy saving, we introduce an extended Markov chain to predict the next activity state and adopt the suitable energy-saving strategy in advance. 1.5 Key Contributions We make the following contributions in this article (a preliminary version of this work appeared in Fan et al. (2015)). ACM Transactions on Sensor Networks, Vol. 13, No. 4, Article 29. Publication date: September 2017