This paper describes a method for assisting pedestrians to cross a road. As motorization develops, pedestrian protection techniques are becoming more and more important. Advanced driving assistance systems (ADAS) are improving rapidly to provide even greater safety. However, since the accident risk of pedestrians remains high, the development of an advanced walking assistance system for pedestrian protection may be an effective means of reducing pedestrian accidents. Crossing a road is one of the highest risk events, and is a complex phenomenon that consists of many dynamically changing elements such as vehicles, traffic signals, bicycles, and the like. A road crossing assistance system requires three items: real-time situational recognition, a robust decision-making function, and reliable information transmission. Edge devices equipped with autonomous systems are one means of achieving these requirements. Situational recognition when crossing a road must identify the pedestrian traffic signals and the crosswalk. Various research has been published regarding the recognition of vehicle traffic signals and crosswalks using in-vehicle cameras. However, since crosswalks (and pedestrians) have conventionally been treated as risks or obstacles for vehicles rather than as guides for crossing, these recognition methods cannot be diverted directly for pedestrian assistance. This paper proposes a novel methodology for walking assistance that includes an image recognition system based on a combination of convolute neural network (CNN) and computational visualization technologies (CV). The proposed methodology also includes a robust judgment algorithm for crossing roads. The proposed method is implemented on edge devices, and its efficacy has been confirmed in field tests. The developed system is considered to be effective and efficient for providing walking assistance.