Light-Weight Spliced Convolution Network-Based Automatic Water Meter Reading in Smart City

Abstract

Automatic reading for water meter is one of the practical demands in smart city applications. Due to the high cost, it is not feasible to replace the old mechanical water meter with a new embedded electronic device. Recently, image recognition based meter reading methods have become research hotspots. However, illumination, occlusion, energy and computational consuming in IoT environment bring challenges to these methods. In this paper, we design and implement a smart water meter reading system to handle this issue. Specifically, we first propose a novel light-weight spliced convolution network to recognize the meter number, which simplifies standard 3 × 3 convolutions by splicing a certain number of 1 × 1 and 3 × 3 size kernel. We then prove the superiority of our network by theoretical analysis. Second, we have implemented the prototype which can handle huge real-time data base on the distributed cloud platform. Base on this system, our system can provide industrial service. Finally, we conduct real-world dataset to verify the performance of the system. The experimental results demonstrate that our proposed light-weight spliced convolution network can reduce nearly 10× computational consuming, 7× model space, and save 3× running time comparing with standard convolution network.INDEX TERMS Water meter reading, spliced convolution network, cyber-physical-system, smart city.

Towards Image-Based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach

“…Prior to the widespread adoption of deep learning in computer vision, most approaches to this task explored image enhancement techniques and handcrafted features with a similar pipeline, i.e., (i) counter detection followed by (ii) digit segmentation and (iii) digit recognition [5], [6]. Most limitations of such methods may be attributed to the fact that handcrafted features are easily affected by noise and are generally not robust to images captured under unconstrained environments [7], [11], [21].…”

“…Although AMR (hereinafter AMR refers to image-based AMR) has received great attention in recent years, most works in the literature are still limited in several ways. In general, the experiments were performed either on propri-etary datasets [4], [10], [15] or on datasets containing images captured on well-controlled environments [3], [11], [16]. This is in stark contrast to related research areas, such as automatic license plate recognition, where in recent years the research focus shifted to unconstrained scenarios (with challenging factors such as blur, various lighting conditions, scale variations, in-plane and out-of-plane rotations, occlusions, etc.)…”

“…In addition, there are many works focused on a single stage of the AMR pipeline [7], [12], [18], which makes it difficult to accurately evaluate the presented methods in an end-to-end manner (e.g., the results achieved by a recognition model may vary considerably depending on how accurate the counter region is detected). Another factor that makes it difficult to assess existing methods, or their applicability, is that the authors commonly do not report the execution time of the proposed approaches or the hardware in which they performed their experiments [11], [16], [18]. Finally, to the best of our knowledge, no previous work dealt with cases where it is not possible to perform the meter reading due to occlusions or faulty meters, even though such cases are relatively common in practice.…”

Pengenalan Karakter Optis untuk Pencatatan Meter Air dengan Long Short Term Memory Recurrent Neural Network

“…Penelitian [13], [14] Penelitian lebih lanjut terkait peningkatan akurasi nilai ganda perlu dilakukan agar akurasi pembacaan secara keseluruhan dapat meningkat. Perubahan data atau perubahan cara training mungkin dibutuhkan.…”

An Integrated IoT Architecture for Smart Metering Using Next Generation Sensor for Water Management Based on LoRaWAN Technology: A Pilot Study

“…The use of smart technologies in measuring systems is a frequent topic in the research, and many various solutions in the area of energy reading (water, gas, or electricity) are described. Jin, G. et al [34] and Li et al [35] proposed a system for measuring water consumption based on image recognition technology, using MCU (Microcontroller unit) STM32F103ZET6 and camera module OV7725. The original image of the water meter counter is preprocessed using greying, edge extraction, Otsu's binarization, and tilt correction.…”