Yaw Estimation Using Cylindrical and Ellipsoidal Face Models

Single image-based head pose estimation with spherical parametrization and 3D morphing

“…They can be further divided into 2 categories coarsely, i.e. geometry distribution based methods [4] [39][40][41][42][43] and 3D facial model [5][6][7][8][9][10] [44][45][46][47][48][49] based methods.…”

“…Batista [10] and Ji and Hu [40] developed an ellipse model on the face region based on the eye locations and estimate head pose angles by finding the relationship between the head pose angles and these ellipse parameters. Similarly, Yao et al [41] and Narayanan et al [42] also adopted an ellipsecircle model to estimate the head pose. Nikolaidis et al [43] distorted the isosceles triangle formed by the two eyes and the mouth to estimate the head yaw angle.…”

“…Since it is hard to get all of the feature points when the absolute yaw and pitch angles are too large, we only selected 7466 images out of a total 15678 images so as to obtain the four feature points accurately by D-CNN [57] and AAM [58]. From Table IV, we can observe that Furthermore, in order to evaluate the performance of the proposed method comprehensively, we have compared the proposed method with some learning based methods (that need additional training processing and a large amount of training data), i.e., the improved Hough-voting with random forest [27], the DVFs and CNN-based method in [35], the fuzzy systems based method in [36], and the ellipsoidal model based geometry method in [42], and Kong's TIP2015 with AAM [49] in Table V for the Pointing'04 database, from which it can be observed that the MAE of the pitch and yaw angle of Proposed-MLFP is the smallest, while the MAE of the pitch and yaw angle of Proposed-ALFP with D-CNN is comparable to the start-of-the-art learning based methods.…”

Head Yaw Estimation using Frontal Face Detector

“…For this reason, this method requires a set of sequential frames and cannot be applied to single images. (Narayanan et al, 2014) studied yaw estimation using cylindrical and ellipsoidal face models. Their study on ellipsoidal framework provides MAE between 4 • and 8 • outperforming manifold-based approaches on FacePix dataset.…”

Usability of Pilot's Gaze in Aeronautic Cockpit for Safer Aircraft

“…Also, all of the feature points need to be visible, which makes these methods very sensitive to occlusion. Methods that use only the center of the head and face boundaries are more robust, more invariant to facial expressions and support a larger breadth of head orientations [4]. A different approach working with facial landmarks was proposed by Zhu et al [5].…”