FASHE: A FrActal Based Strategy for Head Pose Estimation

Bisogni, Carmen; Nappi, Michele; Pero, Chiara; Ricciardi, Stefano

doi:10.1109/tip.2021.3059409

Cited by 22 publications

(17 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The estimation errors are listed in Tables 1 and 2 for Biwi Kinect and AFLW2000 datasets, respectively. From Table 1 it is possible to observe that the average FASHE‐XGBoost MAE is the smallest of all the methods reported, also highlighting a considerable improvement along the pitch axis compared to FASHE approach [15]. Besides, we can also show that the yaw and roll angles of the proposed FASHE‐regression are small, which means that the proposed method is robust and competitive at the state‐of‐the‐art.…”

Section: Resultsmentioning

confidence: 80%

Gradient boosting regression for faster Partitioned Iterated Function Systems‐based head pose estimation

et al. 2021

Self Cite

View full text Add to dashboard Cite

Head pose estimation (HPE) notoriously represents a crucial task for many computer vision applications in robotics, biometry and video surveillance. While, in general, HPE can be performed on both still images and frames extracted from live video or captured footage, its functional approach and the related processing pipeline may have a significant impact on suitability to different application contexts. This implies that, for any real-time application in which HPE is required, this information, namely the angular value of yaw, pitch and roll axes, should be provided in real-time as well. Since, so far, the primary aim in HPE research has been on improving estimation accuracy, there are only a few works reporting the computing time of the proposed HPE method and even less explicitly addressing it. The present work stems from a previous Partitioned Iterated Function Systems-based approach providing state-of-the-art accuracy with high computing cost, and improve it by means of two regression models, namely Gradient Boosting Regressor and Extreme Gradient Boosting Regressor, achieving much faster response and an even lower mean absolute error on the yaw and roll axis, as shown by experiments conducted on the BIWI and AFLW2000 datasets.

show abstract

Section: Resultsmentioning

confidence: 80%

Gradient boosting regression for faster Partitioned Iterated Function Systems‐based head pose estimation

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…As already stated when discussing the implementation in Section 4, this protocol has been initially studied using a simple metric in place of a ML-based regressor. In this regard, the discrimination is effective even without recourse to Machine Learning techniques: row 7 (no ML) compares favorably to rows 1, 2, and 3 [6]. The MAE and yaw figures are especially significant.…”

Section: Discussion and Comparison With The State Of The Artmentioning

confidence: 97%

“…As expected, excluding extreme poses improves the results, even more so than with other methods. Focusing on the comparison with [6] and [4], which do not use ML, shows that a descriptor based on Ricci curvature can be quite effective even when simply used as a metric, without a regression module. The data about Protocol 3 show good results in different conditions, such as a 50/50 training/testing ratio, exclusion of extreme poses.…”

Section: Discussion and Comparison With The State Of The Artmentioning

confidence: 99%

“…The leitmotif of these methods is to obtain a pose estimate from a simple image, without extracting any landmarks. In [6], this approach is adopted without even applying ML techniques. The self-similarities present in a facial image are used to determine a fractal coding vector.…”

Section: Head Pose Estimationmentioning

confidence: 99%

“…Overall, 20 experiments were carried out, rotating the test subject. In the same guise as described in other works, one more experiment was performed using a subset of only 10 subjects [6] [2].…”

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Ollivier-Ricci Curvature For Head Pose Estimation From a Single Image

Cascone¹,

Distasi²,

Nappi³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Head pose estimation is a crucial challenge for many real-world applications, such as attention and human behavior analysis. This paper aims to estimate head pose from a single image by applying notions of network curvature. In the real world, many complex networks have groups of nodes that are well connected to each other with significant functional roles. Similarly, the interactions of facial landmarks can be represented as complex dynamic systems modeled by weighted graphs. The functionalities of such systems are therefore intrinsically linked to the topology and geometry of the underlying graph. In this work, using the geometric notion of Ollivier-Ricci curvature (ORC) on weighted graphs as input to the XGBoost regression model, we show that the intrinsic geometric basis of ORC offers a natural approach to discovering underlying common structure within a pool of poses. Experiments on the BIWI, AFLW2000 and Pointing'04 datasets show that the ORC XGB method performs well compared to state-of-theart methods, both landmark-based and image-only.

show abstract