Energy-Efficient SRAM FPGA-Based Wireless Vision Sensor Node: SENTIOF-CAM

Proceedings of the International Conference on Distributed Smart Cameras

Lawal

2014

Self Cite

Wireless Sensor Networks applications with huge amount of data requirements are attracting the utilization of high performance embedded platforms i.e. Field Programmable Gate Arrays (FPGAs) for in-node sensor processing. However, the design complexity, high configuration and static energies of SRAM FPGAs impose challenges for duty cycled applications. In this demo, we demonstrate the functionality of SRAM FPGA based wireless vision sensor node called SENTIOF-CAM. The demonstration shows that by using intelligent techniques, a low energy and low complexity SRAM FPGA based wireless vision sensor node can be realized for duty cycled applications.

Section: Demonstration Setupmentioning

confidence: 99%

“…The binary image enables the use of binary morphology, erosion followed by dilation in order to remove small noise. Following this, a ROI is extracted and compressed by using G4 bi-level compression scheme [2] [6]. The hardware resource utilization for the aforementioned imaging tasks on Spartan 6 FPGA, XC6SLX16 are shown in Table 1.…”

Section: Vision Tasksmentioning

confidence: 99%

Demo

Proceedings of the International Conference on Distributed Smart Cameras

Lawal

2014

Self Cite

“…An alternative to a processor based solution is to use hardware platforms such as Field Programmable Gate Arrays (FPGAs) which offer advantages of re-configurability and inherit hardware parallelism in order to better exploit a regular flow of initial data centric tasks at lower clock frequency. This results in an improved performance for FPGA by using a small clock frequency as compared to processor based platforms [5]. However, the development time is greater.…”

Section: Introductionmentioning

confidence: 99%

Low complexity FPGA based background subtraction technique for thermal imagery

Proceedings of the 9th International Conference on Distributed Smart Cameras

Munir

et al. 2015

Self Cite

Embedded smart camera systems are gaining popularity for a number of real world surveillance applications. However, there are still challenges, i.e. variation in illumination, shadows, occlusion, and weather conditions while employing the vision algorithms in outdoor environments. For safety-critical surveillance applications, the visual sensors can be complemented with beyond-visual-range sensors. This in turn requires analysis, development and modification of existing imaging techniques. In this work, a low complexity background modelling and subtraction technique has been proposed for thermal imagery. The proposed technique has been implemented on Field Programmable Gate Arrays (FPGAs) after in-depth analysis of different sets of images, characterizing poor signal-to-noise ratio challenges, e.g. motion of high frequency background objects, temperature variation and camera jitter etc. The proposed technique dynamically updates the background on pixel level and requires a single frame storage as opposed to existing techniques. The comparison of this approach with two other approaches show that this approach performs better in different environmental conditions. The proposed technique has been modelled in Register Transfer Logic (RTL) and implementation on the latest FPGAs shows that the design requires less than 1 percent logics, 47 percent block RAMs, and consumes 91 mW power consumption on Artix-7 100T FPGA.

“…Recent advances in the field of electronics, optics and communication are enabling the development of wireless smart camera systems which are expected to have embedded processing for handling large amount of data [1] [2]. These advancements facilitate development of stand-alone, scalable, easy-to-integrate, low cost, and low power solutions for a number of potential applications.…”

Section: Introductionmentioning

confidence: 99%

“…In relation to this, there are three prominent fusion methods applied at different processing levels [3][4], namely pixel, feature, and decision fusing. These approaches are often processed on powerful personal computers, which simplifies the problem because porting a concept to embedded platforms will arise in new set of challenges, for example resources constraints and design complexity [1]. In this paper, we are proposing a visual and infrared based smart camera architecture, which has embedded in-node processing and wireless communication capabilities.…”

Section: Introductionmentioning

confidence: 99%

STC-CAM1, IR-visual based smart camera system

Proceedings of the 9th International Conference on Distributed Smart Cameras

Kardeby

et al. 2015

Self Cite

Safety-critical applications require robust and real-time surveillance. For such applications, a vision sensor alone can give false positive results because of poor lighting conditions, occlusion, or different weather conditions. In this work, a visual sensor is complemented by an infrared thermal sensor which makes the system more resilient in unfavorable situations. In the proposed camera architecture, initial data intensive tasks are performed locally on the sensor node and then compressed data is transmitted to a client device where remaining vision tasks are performed. The proposed camera architecture is demonstrated as a proof-ofconcept and it offers a generic architecture with better surveillance while only performing low complexity computations on the resource constrained devices.