To determine the speed of a vehicle in a collision with body deformation, the kinetic energy input of the vehicle to cause body damage must be estimated. This paper analyzes the methods for estimating the energy equivalent of vehicle damage. A finite element model of a Toyota Yaris developed by the National Crash Analysis Center (NCAC) for use in the LS DYNA R.11.0.0 software environment is used for the simulation. The simulations include tests of the vehicle hitting a non-deformable wall, an object simulating a pole or a tree. The residual deformations obtained are used to determine the energy equivalent speed (EES) values using the “Crash 3—EBS Calculation 12.0” software and a visual comparison with the EES catalog database, where the EES parameter value is recalculated to take into account the difference in the mass of the vehicles.

Fine-grained vehicle orientation estimation is widely reported with strong in-domain accuracy, yet performance degrades substantially when models are applied across datasets; the relative contributions of visual domain shift and annotation label incompatibility to this degradation remain poorly understood. A controlled cross-dataset benchmark was conducted using two publicly available datasets—Car Full View (CFV) and Freiburg Static Cars 52 v1.1 (UnsupCar)—under a fixed ConvNeXt-Small predictor with a varied training source, test target, and image preprocessing strategy. All conditions were evaluated with five-fold cross-validation at the vehicle-instance level. Annotation label incompatibility was identified as the dominant source of transfer error: correcting the angular convention mismatch in UnsupCar orientation labels reduced cross-dataset circular mean absolute error (CMAE) by approximately $3.5$–$4.5^{\circ }$. Crop protocol was a similarly large factor—train/test crop mismatch raised CMAE into the 9–${12}^{\circ }$ range. Square cropping with mirrored boundary padding provided the most robust preprocessing across both in-domain and cross-dataset conditions. After label harmonization, a residual transfer gap of approximately $2^{\circ }$ remained, with a consistent directional asymmetry favoring the UnsupCar-to-CFV transfer direction. Joint training on both harmonized datasets achieved the best-balanced performance ($3.{77}^{\circ }$ on CFV; $5.{38}^{\circ }$ on UnsupCar). These results demonstrate that instance-level splitting, explicit label harmonization, and consistent crop definition are necessary preconditions for credible cross-dataset vehicle orientation evaluation.