Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline

TL;DR

Power battery detection (PBD) is introduced as a new task to localize endpoints of dense plate structures in X-ray images for quality assessment. The authors propose MDCNet, a segmentation-based framework that uses a point segmentation backbone augmented by line and counting predictors and a distance-adaptive ground-truth strategy, guided by a prompt filter to handle interference. They contribute the X-ray PBD dataset with 1,500 labeled images and eight evaluation metrics, and demonstrate that MDCNet outperforms corner detection, density-based counting, and general object detectors on regular, difficult, and tough splits. The work advances automatic PBD by providing a strong, reproducible baseline and a clear benchmark for future research, with planned extensions to 3D CT data and broader industrial applicability.

Abstract

We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluate the quality of power batteries. Existing manufacturers usually rely on human eye observation to complete PBD, which makes it difficult to balance the accuracy and efficiency of detection. To address this issue and drive more attention into this meaningful task, we first elaborately collect a dataset, called X-ray PBD, which has $1,500$ diverse X-ray images selected from thousands of power batteries of $5$ manufacturers, with $7$ different visual interference. Then, we propose a novel segmentation-based solution for PBD, termed multi-dimensional collaborative network (MDCNet). With the help of line and counting predictors, the representation of the point segmentation branch can be improved at both semantic and detail aspects.Besides, we design an effective distance-adaptive mask generation strategy, which can alleviate the visual challenge caused by the inconsistent distribution density of plates to provide MDCNet with stable supervision. Without any bells and whistles, our segmentation-based MDCNet consistently outperforms various other corner detection, crowd counting and general/tiny object detection-based solutions, making it a strong baseline that can help facilitate future research in PBD. Finally, we share some potential difficulties and works for future researches. The source code and datasets will be publicly available at \href{https://github.com/Xiaoqi-Zhao-DLUT/X-ray-PBD}{X-ray PBD}.

Figures (8)

• Figure 1: Illustration of the power battery detection task.
• Figure 2: Examples of various attributes from our X-ray PBD dataset (best viewed zoomed in). See Tab. \ref{['tab:attribute_description']} for details.
• Figure 3: Statistics of the X-ray PBD dataset. (a) Taxonomic of interference and shots. (b) Overhang distributions. (c) Number distributions. (d) Co-occurrence distribution of attributes. (e) Multi-dependencies among these attributes.
• Figure 4: Overview of our MDCNet. It contains a shared encoder to extract different level features for the prompt and current images, respectively. Multi-scale module is only embedded in the high-level features. Prompt filter module are used to combine the prompt and current features to generate a series of filtered features. Point predictor include five decoder layers to produce point segmentation maps. Counting and line predictors are guided by the point prediction and fusing high-level and low-level features, respectively.
• Figure 5: Detailed illustration of each component.