Intelligent video surveillance (IVS) is always an interesting research topic to utilize visual analysis algorithms for exploring richly structured information from big surveillance data. However, existing IVS systems either struggle to utilize computing resources adequately to improve the efficiency of large-scale video analysis, or present a customized system for specific video analytic functions. It still lacks of a comprehensive computing architecture to enhance efficiency, extensibility and flexibility of IVS system. Moreover, it is also an open problem to study the effect of the combinations of multiple vision modules on the final performance of end applications of IVS system. Motivated by these challenges, we develop an Intelligent Scene Exploration and Evaluation (ISEE) platform based on a heterogeneous CPU-GPU cluster and some distributed computing tools, where Spark Streaming serves as the computing engine for efficient large-scale video processing and Kafka is adopted as a middle-ware message center to decouple different analysis modules flexibly. To validate the efficiency of the ISEE and study the evaluation problem on composable systems, we instantiate the ISEE for an end application on person retrieval with three visual analysis modules, including pedestrian detection with tracking, attribute recognition and re-identification. Extensive experiments are performed on a large-scale surveillance video dataset involving 25 camera scenes, totally 587 hours 720p synchronous videos, where a two-stage question-answering procedure is proposed to measure the performance of execution pipelines composed of multiple visual analysis algorithms based on millions of attribute-based and relationship-based queries. The case study of system-level evaluations may inspire researchers to improve visual analysis algorithms and combining strategies from the view of a scalable and composable system in the future.

Cancerous tissues have electrical-conductivity signatures different from normal tissues, which contain potentially useful information for early detection. Despite recent advancements in electrical-conductivity imaging and its applications, imaging electrical conductivities with high spatial resolution remains a challenge for non-invasive diagnosis of early-stage cancer. Among the various electrical-conductivity imaging methods, magnetoacoustic tomography with magnetic induction (MAT-MI) is a promising technology for non-invasive detection of breast cancer. However, previous efforts to use MAT-MI for cancer imaging have suffered due to insufficient spatial resolution. In this work, we have developed a high-frequency MAT-MI (hfMAT-MI) system with a 2-D spatial resolution of 1 mm, a significant improvement over previous methods. Furthermore, we demonstrated the performance of this method using an in vivo cancer model in nude mice with human breast xenograft hindlimb tumors. hfMAT-MI was able to resolve not only the boundaries between cancerous and healthy tissues, but also the tumors' internal structures. Importantly, we were able to track a growing tumor using our hfMAT-MI method for the first time in an in vivo mouse model, demonstrating the promise of this magneto-acoustic imaging system for effective detection and diagnosis of early-stage breast cancer.