POISON: Human Pose Estimation in Insufficient Lighting Conditions Using Sensor Fusion

Crescitelli, Viviana; Kosuge, Atsutake; Oshima, Takashi

doi:10.1109/tim.2020.3043872

Cited by 19 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) technology has been widely studied to automate various manual tasks. The introduction of AI technology is expected to improve safety, such as in advanced driver assistance systems (ADAS) [1], [2], and factory productivity, such as in factory automation [3].…”

Section: Introductionmentioning

confidence: 99%

“…While there is demand for such visual inspection technologies, their use in the food and optical equipment industries is difficult. The major technical challenges of applying conventional visual inspection systems to such industries are (1) reflective target objects that are common in the food industry, such as transparent plastic wrapping bags [see Fig. 1(a)], and (2) transparent target objects that are common in both the food and optical industries, such as objects made of plastic and glass [see Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Metric Learning-Based Anomaly Detection System for Transparent Objects Using Polarized-Image Fusion

Kosuge

Hamada

et al. 2023

IEEE Open J. Ind. Electron. Soc.

Self Cite

View full text Add to dashboard Cite

While visual inspection systems have been widely used in many industries, their use in the food and optical equipment industries has been limited. Transparent and reflective materials are often used in these applications, but existing anomaly detection (AD) systems have low accuracy in their detection due to low visibility. Here, we developed an AD system using a polarization camera for reflective and transparent target objects. Two new techniques are developed. First is the polarized image fusion (PIF) technique which suppresses glare from reflective surfaces while highlighting transparent foreign objects. In PIF, four captured polarized images are fused to synthesize a high-quality image according to calculated weight coefficients. The second new technique is an ArcObj-based deep metric learning technique to improve AD accuracy. The proposed system was evaluated in experiments on three datasets: cookie samples wrapped in transparent plastic bags; transparent plastic bottles; and transparent lenses. High AD accuracies in terms of the area under the receiver operating characteristic curve (AUC) were achieved: 0.88 AUC for the cookie dataset; 0.87 AUC for the bottle dataset; and 0.98 AUC for the lens dataset. Compared to the state-of-the-art AD algorithm (Patchcore), the proposed method improved AD accuracy by 0.09 AUC.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%