In-baggage Suspicious Object Detection Using WiFi

Project Objectives

The growing needs of public safety urgently require scalable and low-cost techniques for detecting dangerous objects (e.g., lethal weapons, homemade-bombs, explosive chemicals) hidden in baggage. Traditional baggage check involves either high manpower for manual examinations or expensive and specialized instruments, such as X-ray and computed tomography (CT). The objective of this project is to design a low-cost and easy-to-scale system that utilizes commodity WiFi to detect suspicious objects in baggage.

Technology Rationale

Most dangerous objects such as weapons, homemade bombs, and explosives, are usually metal or liquid, which have significant interference (e.g., absorption, refraction, and reflection) to wireless signals, while baggage is usually made of fiber, plastics, or paper that allow wireless signals to pass through. Such different impacts to wireless signals suggest that it is possible to use wireless signals for detecting and identifying suspicious objects hidden in baggage. In this project, we leverage channel state information (CSI), which is readily available in current WiFi systems, to detect liquid/metal objects and estimate their sizes. We find that the amplitude and phase of CSI capture rich material and shape characteristics of the object as shown in Figure 1. 

Charts showing different objects' interference to the Wi-Fi signal (in CSI amplitude)

Technical Approach

To identify different materials, we exploit the WiFi signals transmitting through or bypassing the object as shown in Figure 2 (a), which results in different characteristics (i.e., absorption, refraction, and reflection) in the CSI measurements from antennas and their differences. Additionally, as shown in Figure 2 (b), we also extract the signal reflected by the object from CSI to estimate its shape (e.g., width and height) or volume. We find that the strength of the reflected signal is proportional to the reflection area of the object. Given the CSI measurements of the object, our system first calibrates the phase value in CSI to remove the impacts of hardware noises and then leverages a two-step method to perform material detection. Particularly, we first differentiate the metal and liquid objects from other objects in baggage. Upon detecting metal/liquid objects, our system will run a risk estimation module to estimate the object shape based on wireless signals reflected from the objects. 

Project Status

The paper from this project was awarded as the best paper of IEEE CNS 2018. Our system can detect liquid and metal objects with over 95% accuracy as shown in Figure 3. We also show that our system has less than 0.3cm and 0.5cm errors to estimate the object’s width and height. 

Charts showing different objects detection accuracy and size estimation error.

References

Chen Wang, Jian Liu, Yingying Chen, Hongbo Liu, and Yan Wang. Towards In-baggage Suspicious Object Detection Using Commodity WiFi. In Proceedings of the International Conference on Communications and Network Security (IEEE CNS), pp. 1-9, 2018. (Best Paper Award)